talk-data.com
People (6 results)
See all 6 →Activities & events
| Title & Speakers | Event |
|---|---|
|
Tarek A. Atwan
– author
Perform time series analysis and forecasting confidently with this Python code bank and reference manual Purchase of the print or Kindle book includes a free PDF eBook Key Features Explore up-to-date forecasting and anomaly detection techniques using statistical, machine learning, and deep learning algorithms Learn different techniques for evaluating, diagnosing, and optimizing your models Work with a variety of complex data with trends, multiple seasonal patterns, and irregularities Book Description To use time series data to your advantage, you need to be well-versed in data preparation, analysis, and forecasting. This fully updated second edition includes chapters on probabilistic models and signal processing techniques, as well as new content on transformers. Additionally, you will leverage popular libraries and their latest releases covering Pandas, Polars, Sktime, stats models, stats forecast, Darts, and Prophet for time series with new and relevant examples. You'll start by ingesting time series data from various sources and formats, and learn strategies for handling missing data, dealing with time zones and custom business days, and detecting anomalies using intuitive statistical methods. Further, you'll explore forecasting using classical statistical models (Holt-Winters, SARIMA, and VAR). Learn practical techniques for handling non-stationary data, using power transforms, ACF and PACF plots, and decomposing time series data with multiple seasonal patterns. Then we will move into more advanced topics such as building ML and DL models using TensorFlow and PyTorch, and explore probabilistic modeling techniques. In this part, you’ll also learn how to evaluate, compare, and optimize models, making sure that you finish this book well-versed in wrangling data with Python. What you will learn Understand what makes time series data different from other data Apply imputation and interpolation strategies to handle missing data Implement an array of models for univariate and multivariate time series Plot interactive time series visualizations using hvPlot Explore state-space models and the unobserved components model (UCM) Detect anomalies using statistical and machine learning methods Forecast complex time series with multiple seasonal patterns Use conformal prediction for constructing prediction intervals for time series Who this book is for This book is for data analysts, business analysts, data scientists, data engineers, and Python developers who want practical Python recipes for time series analysis and forecasting techniques. Fundamental knowledge of Python programming is a prerequisite. Prior experience working with time series data to solve business problems will also help you to better utilize and apply the different recipes in this book. |
O'Reilly Data Science Books
|
|
Oct 30 - AI, ML and Computer Vision Meetup
2025-10-30 · 16:00
Join the virtual Meetup to hear talks from experts on cutting-edge topics across AI, ML, and computer vision. Date, Time and Location Oct 30, 2025 9 AM Pacific Online. Register for the Zoom! The Agent Factory: Building a Platform for Enterprise-Wide AI Automation In this talk we will explore what it takes to build an enterprise-ready AI automation platform at scale. The topics covered will include:
About the Speaker Virender Bhargav at Flipkart is a seasoned engineering leader whose expertise spans business technology integration, enterprise applications, system design/architecture, and building highly scalable systems. With a deep understanding of technology, he has spearheaded teams, modernized technology landscapes, and managed core platform layers and strategic products. With extensive experience driving innovation at companies like Paytm and Flipkart, his contributions have left a lasting impact on the industry. Scaling Generative Models at Scale with Ray and PyTorch Generative image models like Stable Diffusion have opened up exciting possibilities for personalization, creativity, and scalable deployment. However, fine-tuning them in production‐grade settings poses challenges: managing compute, hyperparameters, model size, data, and distributed coordination are nontrivial. In this talk, we’ll dive deep into learning how to fine-tune Stable Diffusion models using Ray Train (with HuggingFace Diffusers), including approaches like DreamBooth and LoRA. We’ll cover what works (and what doesn’t) in scaling out training jobs, handling large data, optimizing for GPU memory and speed, and validating outputs. Attendees will come away with practical insights and patterns they can use to fine-tune generative models in their own work. About the Speaker Suman Debnath is a Technical Lead (ML) at Anyscale, where he focuses on distributed training, fine-tuning, and inference optimization at scale on the cloud. His work centers around building and optimizing end-to-end machine learning workflows powered by distributed computing framework like Ray, enabling scalable and efficient ML systems. Suman’s expertise spans Natural Language Processing (NLP), Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG). Earlier in his career, he developed performance benchmarking and monitoring tools for distributed storage systems. Beyond engineering, Suman is an active community contributor, having spoken at over 100 global conferences and events, including PyCon, PyData, ODSC, AIE and numerous meetups worldwide. Privacy-preserving in Computer Vision through Optics Learning Cameras are now ubiquitous, powering computer vision systems that assist us in everyday tasks and critical settings such as operating rooms. Yet, their widespread use raises serious privacy concerns: traditional cameras are designed to capture high-resolution images, making it easy to identify sensitive attributes such as faces, nudity, or personal objects. Once acquired, such data can be misused if accessed by adversaries. Existing software-based privacy mechanisms, such as blurring or pixelation, often degrade task performance and leave vulnerabilities in the processing pipeline. In this talk, we explore an alternative question: how can we preserve privacy before or during image acquisition? By revisiting the image formation model, we show how camera optics themselves can be learned and optimized to acquire images that are unintelligible to humans yet remain useful for downstream vision tasks like action recognition. We will discuss recent approaches to learning camera lenses that intentionally produce privacy-preserving images, blurry and unrecognizable to the human eye, but still effective for machine perception. This paradigm shift opens the door to a new generation of cameras that embed privacy directly into their hardware design. About the Speaker Carlos Hinojosa is a Postdoctoral researcher at King Abdullah University of Science and Technology (KAUST) working with Prof. Bernard Ghanem. His research interests span Computer Vision, Machine Learning, AI Safety, and AI for Science. He focuses on developing safe, accurate, and efficient vision systems and machine-learning models that can reliably perceive, understand, and act on information, while ensuring robustness, protecting privacy, and aligning with societal values. It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data Can we match vision and language embeddings without any supervision? According to the platonic representation hypothesis, as model and dataset scales increase, distances between corresponding representations are becoming similar in both embedding spaces. Our study demonstrates that pairwise distances are often sufficient to enable unsupervised matching, allowing vision-language correspondences to be discovered without any parallel data. About the Speaker Dominik Schnaus is a third-year Ph.D. student in the Computer Vision Group at the Technical University of Munich (TUM), supervised by Daniel Cremers. His research centers on multimodal and self-supervised learning with a special emphasis on understanding similarities across embedding spaces of different modalities. |
Oct 30 - AI, ML and Computer Vision Meetup
|
|
Oct 30 - AI, ML and Computer Vision Meetup
2025-10-30 · 16:00
Join the virtual Meetup to hear talks from experts on cutting-edge topics across AI, ML, and computer vision. Date, Time and Location Oct 30, 2025 9 AM Pacific Online. Register for the Zoom! The Agent Factory: Building a Platform for Enterprise-Wide AI Automation In this talk we will explore what it takes to build an enterprise-ready AI automation platform at scale. The topics covered will include:
About the Speaker Virender Bhargav at Flipkart is a seasoned engineering leader whose expertise spans business technology integration, enterprise applications, system design/architecture, and building highly scalable systems. With a deep understanding of technology, he has spearheaded teams, modernized technology landscapes, and managed core platform layers and strategic products. With extensive experience driving innovation at companies like Paytm and Flipkart, his contributions have left a lasting impact on the industry. Scaling Generative Models at Scale with Ray and PyTorch Generative image models like Stable Diffusion have opened up exciting possibilities for personalization, creativity, and scalable deployment. However, fine-tuning them in production‐grade settings poses challenges: managing compute, hyperparameters, model size, data, and distributed coordination are nontrivial. In this talk, we’ll dive deep into learning how to fine-tune Stable Diffusion models using Ray Train (with HuggingFace Diffusers), including approaches like DreamBooth and LoRA. We’ll cover what works (and what doesn’t) in scaling out training jobs, handling large data, optimizing for GPU memory and speed, and validating outputs. Attendees will come away with practical insights and patterns they can use to fine-tune generative models in their own work. About the Speaker Suman Debnath is a Technical Lead (ML) at Anyscale, where he focuses on distributed training, fine-tuning, and inference optimization at scale on the cloud. His work centers around building and optimizing end-to-end machine learning workflows powered by distributed computing framework like Ray, enabling scalable and efficient ML systems. Suman’s expertise spans Natural Language Processing (NLP), Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG). Earlier in his career, he developed performance benchmarking and monitoring tools for distributed storage systems. Beyond engineering, Suman is an active community contributor, having spoken at over 100 global conferences and events, including PyCon, PyData, ODSC, AIE and numerous meetups worldwide. Privacy-preserving in Computer Vision through Optics Learning Cameras are now ubiquitous, powering computer vision systems that assist us in everyday tasks and critical settings such as operating rooms. Yet, their widespread use raises serious privacy concerns: traditional cameras are designed to capture high-resolution images, making it easy to identify sensitive attributes such as faces, nudity, or personal objects. Once acquired, such data can be misused if accessed by adversaries. Existing software-based privacy mechanisms, such as blurring or pixelation, often degrade task performance and leave vulnerabilities in the processing pipeline. In this talk, we explore an alternative question: how can we preserve privacy before or during image acquisition? By revisiting the image formation model, we show how camera optics themselves can be learned and optimized to acquire images that are unintelligible to humans yet remain useful for downstream vision tasks like action recognition. We will discuss recent approaches to learning camera lenses that intentionally produce privacy-preserving images, blurry and unrecognizable to the human eye, but still effective for machine perception. This paradigm shift opens the door to a new generation of cameras that embed privacy directly into their hardware design. About the Speaker Carlos Hinojosa is a Postdoctoral researcher at King Abdullah University of Science and Technology (KAUST) working with Prof. Bernard Ghanem. His research interests span Computer Vision, Machine Learning, AI Safety, and AI for Science. He focuses on developing safe, accurate, and efficient vision systems and machine-learning models that can reliably perceive, understand, and act on information, while ensuring robustness, protecting privacy, and aligning with societal values. It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data Can we match vision and language embeddings without any supervision? According to the platonic representation hypothesis, as model and dataset scales increase, distances between corresponding representations are becoming similar in both embedding spaces. Our study demonstrates that pairwise distances are often sufficient to enable unsupervised matching, allowing vision-language correspondences to be discovered without any parallel data. About the Speaker Dominik Schnaus is a third-year Ph.D. student in the Computer Vision Group at the Technical University of Munich (TUM), supervised by Daniel Cremers. His research centers on multimodal and self-supervised learning with a special emphasis on understanding similarities across embedding spaces of different modalities. |
Oct 30 - AI, ML and Computer Vision Meetup
|
|
Oct 30 - AI, ML and Computer Vision Meetup
2025-10-30 · 16:00
Join the virtual Meetup to hear talks from experts on cutting-edge topics across AI, ML, and computer vision. Date, Time and Location Oct 30, 2025 9 AM Pacific Online. Register for the Zoom! The Agent Factory: Building a Platform for Enterprise-Wide AI Automation In this talk we will explore what it takes to build an enterprise-ready AI automation platform at scale. The topics covered will include:
About the Speaker Virender Bhargav at Flipkart is a seasoned engineering leader whose expertise spans business technology integration, enterprise applications, system design/architecture, and building highly scalable systems. With a deep understanding of technology, he has spearheaded teams, modernized technology landscapes, and managed core platform layers and strategic products. With extensive experience driving innovation at companies like Paytm and Flipkart, his contributions have left a lasting impact on the industry. Scaling Generative Models at Scale with Ray and PyTorch Generative image models like Stable Diffusion have opened up exciting possibilities for personalization, creativity, and scalable deployment. However, fine-tuning them in production‐grade settings poses challenges: managing compute, hyperparameters, model size, data, and distributed coordination are nontrivial. In this talk, we’ll dive deep into learning how to fine-tune Stable Diffusion models using Ray Train (with HuggingFace Diffusers), including approaches like DreamBooth and LoRA. We’ll cover what works (and what doesn’t) in scaling out training jobs, handling large data, optimizing for GPU memory and speed, and validating outputs. Attendees will come away with practical insights and patterns they can use to fine-tune generative models in their own work. About the Speaker Suman Debnath is a Technical Lead (ML) at Anyscale, where he focuses on distributed training, fine-tuning, and inference optimization at scale on the cloud. His work centers around building and optimizing end-to-end machine learning workflows powered by distributed computing framework like Ray, enabling scalable and efficient ML systems. Suman’s expertise spans Natural Language Processing (NLP), Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG). Earlier in his career, he developed performance benchmarking and monitoring tools for distributed storage systems. Beyond engineering, Suman is an active community contributor, having spoken at over 100 global conferences and events, including PyCon, PyData, ODSC, AIE and numerous meetups worldwide. Privacy-preserving in Computer Vision through Optics Learning Cameras are now ubiquitous, powering computer vision systems that assist us in everyday tasks and critical settings such as operating rooms. Yet, their widespread use raises serious privacy concerns: traditional cameras are designed to capture high-resolution images, making it easy to identify sensitive attributes such as faces, nudity, or personal objects. Once acquired, such data can be misused if accessed by adversaries. Existing software-based privacy mechanisms, such as blurring or pixelation, often degrade task performance and leave vulnerabilities in the processing pipeline. In this talk, we explore an alternative question: how can we preserve privacy before or during image acquisition? By revisiting the image formation model, we show how camera optics themselves can be learned and optimized to acquire images that are unintelligible to humans yet remain useful for downstream vision tasks like action recognition. We will discuss recent approaches to learning camera lenses that intentionally produce privacy-preserving images, blurry and unrecognizable to the human eye, but still effective for machine perception. This paradigm shift opens the door to a new generation of cameras that embed privacy directly into their hardware design. About the Speaker Carlos Hinojosa is a Postdoctoral researcher at King Abdullah University of Science and Technology (KAUST) working with Prof. Bernard Ghanem. His research interests span Computer Vision, Machine Learning, AI Safety, and AI for Science. He focuses on developing safe, accurate, and efficient vision systems and machine-learning models that can reliably perceive, understand, and act on information, while ensuring robustness, protecting privacy, and aligning with societal values. It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data Can we match vision and language embeddings without any supervision? According to the platonic representation hypothesis, as model and dataset scales increase, distances between corresponding representations are becoming similar in both embedding spaces. Our study demonstrates that pairwise distances are often sufficient to enable unsupervised matching, allowing vision-language correspondences to be discovered without any parallel data. About the Speaker Dominik Schnaus is a third-year Ph.D. student in the Computer Vision Group at the Technical University of Munich (TUM), supervised by Daniel Cremers. His research centers on multimodal and self-supervised learning with a special emphasis on understanding similarities across embedding spaces of different modalities. |
Oct 30 - AI, ML and Computer Vision Meetup
|
|
Oct 30 - AI, ML and Computer Vision Meetup
2025-10-30 · 16:00
Join the virtual Meetup to hear talks from experts on cutting-edge topics across AI, ML, and computer vision. Date, Time and Location Oct 30, 2025 9 AM Pacific Online. Register for the Zoom! The Agent Factory: Building a Platform for Enterprise-Wide AI Automation In this talk we will explore what it takes to build an enterprise-ready AI automation platform at scale. The topics covered will include:
About the Speaker Virender Bhargav at Flipkart is a seasoned engineering leader whose expertise spans business technology integration, enterprise applications, system design/architecture, and building highly scalable systems. With a deep understanding of technology, he has spearheaded teams, modernized technology landscapes, and managed core platform layers and strategic products. With extensive experience driving innovation at companies like Paytm and Flipkart, his contributions have left a lasting impact on the industry. Scaling Generative Models at Scale with Ray and PyTorch Generative image models like Stable Diffusion have opened up exciting possibilities for personalization, creativity, and scalable deployment. However, fine-tuning them in production‐grade settings poses challenges: managing compute, hyperparameters, model size, data, and distributed coordination are nontrivial. In this talk, we’ll dive deep into learning how to fine-tune Stable Diffusion models using Ray Train (with HuggingFace Diffusers), including approaches like DreamBooth and LoRA. We’ll cover what works (and what doesn’t) in scaling out training jobs, handling large data, optimizing for GPU memory and speed, and validating outputs. Attendees will come away with practical insights and patterns they can use to fine-tune generative models in their own work. About the Speaker Suman Debnath is a Technical Lead (ML) at Anyscale, where he focuses on distributed training, fine-tuning, and inference optimization at scale on the cloud. His work centers around building and optimizing end-to-end machine learning workflows powered by distributed computing framework like Ray, enabling scalable and efficient ML systems. Suman’s expertise spans Natural Language Processing (NLP), Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG). Earlier in his career, he developed performance benchmarking and monitoring tools for distributed storage systems. Beyond engineering, Suman is an active community contributor, having spoken at over 100 global conferences and events, including PyCon, PyData, ODSC, AIE and numerous meetups worldwide. Privacy-preserving in Computer Vision through Optics Learning Cameras are now ubiquitous, powering computer vision systems that assist us in everyday tasks and critical settings such as operating rooms. Yet, their widespread use raises serious privacy concerns: traditional cameras are designed to capture high-resolution images, making it easy to identify sensitive attributes such as faces, nudity, or personal objects. Once acquired, such data can be misused if accessed by adversaries. Existing software-based privacy mechanisms, such as blurring or pixelation, often degrade task performance and leave vulnerabilities in the processing pipeline. In this talk, we explore an alternative question: how can we preserve privacy before or during image acquisition? By revisiting the image formation model, we show how camera optics themselves can be learned and optimized to acquire images that are unintelligible to humans yet remain useful for downstream vision tasks like action recognition. We will discuss recent approaches to learning camera lenses that intentionally produce privacy-preserving images, blurry and unrecognizable to the human eye, but still effective for machine perception. This paradigm shift opens the door to a new generation of cameras that embed privacy directly into their hardware design. About the Speaker Carlos Hinojosa is a Postdoctoral researcher at King Abdullah University of Science and Technology (KAUST) working with Prof. Bernard Ghanem. His research interests span Computer Vision, Machine Learning, AI Safety, and AI for Science. He focuses on developing safe, accurate, and efficient vision systems and machine-learning models that can reliably perceive, understand, and act on information, while ensuring robustness, protecting privacy, and aligning with societal values. It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data Can we match vision and language embeddings without any supervision? According to the platonic representation hypothesis, as model and dataset scales increase, distances between corresponding representations are becoming similar in both embedding spaces. Our study demonstrates that pairwise distances are often sufficient to enable unsupervised matching, allowing vision-language correspondences to be discovered without any parallel data. About the Speaker Dominik Schnaus is a third-year Ph.D. student in the Computer Vision Group at the Technical University of Munich (TUM), supervised by Daniel Cremers. His research centers on multimodal and self-supervised learning with a special emphasis on understanding similarities across embedding spaces of different modalities. |
Oct 30 - AI, ML and Computer Vision Meetup
|
|
Oct 30 - AI, ML and Computer Vision Meetup
2025-10-30 · 16:00
Join the virtual Meetup to hear talks from experts on cutting-edge topics across AI, ML, and computer vision. Date, Time and Location Oct 30, 2025 9 AM Pacific Online. Register for the Zoom! The Agent Factory: Building a Platform for Enterprise-Wide AI Automation In this talk we will explore what it takes to build an enterprise-ready AI automation platform at scale. The topics covered will include:
About the Speaker Virender Bhargav at Flipkart is a seasoned engineering leader whose expertise spans business technology integration, enterprise applications, system design/architecture, and building highly scalable systems. With a deep understanding of technology, he has spearheaded teams, modernized technology landscapes, and managed core platform layers and strategic products. With extensive experience driving innovation at companies like Paytm and Flipkart, his contributions have left a lasting impact on the industry. Scaling Generative Models at Scale with Ray and PyTorch Generative image models like Stable Diffusion have opened up exciting possibilities for personalization, creativity, and scalable deployment. However, fine-tuning them in production‐grade settings poses challenges: managing compute, hyperparameters, model size, data, and distributed coordination are nontrivial. In this talk, we’ll dive deep into learning how to fine-tune Stable Diffusion models using Ray Train (with HuggingFace Diffusers), including approaches like DreamBooth and LoRA. We’ll cover what works (and what doesn’t) in scaling out training jobs, handling large data, optimizing for GPU memory and speed, and validating outputs. Attendees will come away with practical insights and patterns they can use to fine-tune generative models in their own work. About the Speaker Suman Debnath is a Technical Lead (ML) at Anyscale, where he focuses on distributed training, fine-tuning, and inference optimization at scale on the cloud. His work centers around building and optimizing end-to-end machine learning workflows powered by distributed computing framework like Ray, enabling scalable and efficient ML systems. Suman’s expertise spans Natural Language Processing (NLP), Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG). Earlier in his career, he developed performance benchmarking and monitoring tools for distributed storage systems. Beyond engineering, Suman is an active community contributor, having spoken at over 100 global conferences and events, including PyCon, PyData, ODSC, AIE and numerous meetups worldwide. Privacy-preserving in Computer Vision through Optics Learning Cameras are now ubiquitous, powering computer vision systems that assist us in everyday tasks and critical settings such as operating rooms. Yet, their widespread use raises serious privacy concerns: traditional cameras are designed to capture high-resolution images, making it easy to identify sensitive attributes such as faces, nudity, or personal objects. Once acquired, such data can be misused if accessed by adversaries. Existing software-based privacy mechanisms, such as blurring or pixelation, often degrade task performance and leave vulnerabilities in the processing pipeline. In this talk, we explore an alternative question: how can we preserve privacy before or during image acquisition? By revisiting the image formation model, we show how camera optics themselves can be learned and optimized to acquire images that are unintelligible to humans yet remain useful for downstream vision tasks like action recognition. We will discuss recent approaches to learning camera lenses that intentionally produce privacy-preserving images, blurry and unrecognizable to the human eye, but still effective for machine perception. This paradigm shift opens the door to a new generation of cameras that embed privacy directly into their hardware design. About the Speaker Carlos Hinojosa is a Postdoctoral researcher at King Abdullah University of Science and Technology (KAUST) working with Prof. Bernard Ghanem. His research interests span Computer Vision, Machine Learning, AI Safety, and AI for Science. He focuses on developing safe, accurate, and efficient vision systems and machine-learning models that can reliably perceive, understand, and act on information, while ensuring robustness, protecting privacy, and aligning with societal values. It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data Can we match vision and language embeddings without any supervision? According to the platonic representation hypothesis, as model and dataset scales increase, distances between corresponding representations are becoming similar in both embedding spaces. Our study demonstrates that pairwise distances are often sufficient to enable unsupervised matching, allowing vision-language correspondences to be discovered without any parallel data. About the Speaker Dominik Schnaus is a third-year Ph.D. student in the Computer Vision Group at the Technical University of Munich (TUM), supervised by Daniel Cremers. His research centers on multimodal and self-supervised learning with a special emphasis on understanding similarities across embedding spaces of different modalities. |
Oct 30 - AI, ML and Computer Vision Meetup
|
|
Oct 30 - AI, ML and Computer Vision Meetup
2025-10-30 · 16:00
Join the virtual Meetup to hear talks from experts on cutting-edge topics across AI, ML, and computer vision. Date, Time and Location Oct 30, 2025 9 AM Pacific Online. Register for the Zoom! The Agent Factory: Building a Platform for Enterprise-Wide AI Automation In this talk we will explore what it takes to build an enterprise-ready AI automation platform at scale. The topics covered will include:
About the Speaker Virender Bhargav at Flipkart is a seasoned engineering leader whose expertise spans business technology integration, enterprise applications, system design/architecture, and building highly scalable systems. With a deep understanding of technology, he has spearheaded teams, modernized technology landscapes, and managed core platform layers and strategic products. With extensive experience driving innovation at companies like Paytm and Flipkart, his contributions have left a lasting impact on the industry. Scaling Generative Models at Scale with Ray and PyTorch Generative image models like Stable Diffusion have opened up exciting possibilities for personalization, creativity, and scalable deployment. However, fine-tuning them in production‐grade settings poses challenges: managing compute, hyperparameters, model size, data, and distributed coordination are nontrivial. In this talk, we’ll dive deep into learning how to fine-tune Stable Diffusion models using Ray Train (with HuggingFace Diffusers), including approaches like DreamBooth and LoRA. We’ll cover what works (and what doesn’t) in scaling out training jobs, handling large data, optimizing for GPU memory and speed, and validating outputs. Attendees will come away with practical insights and patterns they can use to fine-tune generative models in their own work. About the Speaker Suman Debnath is a Technical Lead (ML) at Anyscale, where he focuses on distributed training, fine-tuning, and inference optimization at scale on the cloud. His work centers around building and optimizing end-to-end machine learning workflows powered by distributed computing framework like Ray, enabling scalable and efficient ML systems. Suman’s expertise spans Natural Language Processing (NLP), Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG). Earlier in his career, he developed performance benchmarking and monitoring tools for distributed storage systems. Beyond engineering, Suman is an active community contributor, having spoken at over 100 global conferences and events, including PyCon, PyData, ODSC, AIE and numerous meetups worldwide. Privacy-preserving in Computer Vision through Optics Learning Cameras are now ubiquitous, powering computer vision systems that assist us in everyday tasks and critical settings such as operating rooms. Yet, their widespread use raises serious privacy concerns: traditional cameras are designed to capture high-resolution images, making it easy to identify sensitive attributes such as faces, nudity, or personal objects. Once acquired, such data can be misused if accessed by adversaries. Existing software-based privacy mechanisms, such as blurring or pixelation, often degrade task performance and leave vulnerabilities in the processing pipeline. In this talk, we explore an alternative question: how can we preserve privacy before or during image acquisition? By revisiting the image formation model, we show how camera optics themselves can be learned and optimized to acquire images that are unintelligible to humans yet remain useful for downstream vision tasks like action recognition. We will discuss recent approaches to learning camera lenses that intentionally produce privacy-preserving images, blurry and unrecognizable to the human eye, but still effective for machine perception. This paradigm shift opens the door to a new generation of cameras that embed privacy directly into their hardware design. About the Speaker Carlos Hinojosa is a Postdoctoral researcher at King Abdullah University of Science and Technology (KAUST) working with Prof. Bernard Ghanem. His research interests span Computer Vision, Machine Learning, AI Safety, and AI for Science. He focuses on developing safe, accurate, and efficient vision systems and machine-learning models that can reliably perceive, understand, and act on information, while ensuring robustness, protecting privacy, and aligning with societal values. It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data Can we match vision and language embeddings without any supervision? According to the platonic representation hypothesis, as model and dataset scales increase, distances between corresponding representations are becoming similar in both embedding spaces. Our study demonstrates that pairwise distances are often sufficient to enable unsupervised matching, allowing vision-language correspondences to be discovered without any parallel data. About the Speaker Dominik Schnaus is a third-year Ph.D. student in the Computer Vision Group at the Technical University of Munich (TUM), supervised by Daniel Cremers. His research centers on multimodal and self-supervised learning with a special emphasis on understanding similarities across embedding spaces of different modalities. |
Oct 30 - AI, ML and Computer Vision Meetup
|
|
Oct 30 - AI, ML and Computer Vision Meetup
2025-10-30 · 16:00
Join the virtual Meetup to hear talks from experts on cutting-edge topics across AI, ML, and computer vision. Date, Time and Location Oct 30, 2025 9 AM Pacific Online. Register for the Zoom! The Agent Factory: Building a Platform for Enterprise-Wide AI Automation In this talk we will explore what it takes to build an enterprise-ready AI automation platform at scale. The topics covered will include:
About the Speaker Virender Bhargav at Flipkart is a seasoned engineering leader whose expertise spans business technology integration, enterprise applications, system design/architecture, and building highly scalable systems. With a deep understanding of technology, he has spearheaded teams, modernized technology landscapes, and managed core platform layers and strategic products. With extensive experience driving innovation at companies like Paytm and Flipkart, his contributions have left a lasting impact on the industry. Scaling Generative Models at Scale with Ray and PyTorch Generative image models like Stable Diffusion have opened up exciting possibilities for personalization, creativity, and scalable deployment. However, fine-tuning them in production‐grade settings poses challenges: managing compute, hyperparameters, model size, data, and distributed coordination are nontrivial. In this talk, we’ll dive deep into learning how to fine-tune Stable Diffusion models using Ray Train (with HuggingFace Diffusers), including approaches like DreamBooth and LoRA. We’ll cover what works (and what doesn’t) in scaling out training jobs, handling large data, optimizing for GPU memory and speed, and validating outputs. Attendees will come away with practical insights and patterns they can use to fine-tune generative models in their own work. About the Speaker Suman Debnath is a Technical Lead (ML) at Anyscale, where he focuses on distributed training, fine-tuning, and inference optimization at scale on the cloud. His work centers around building and optimizing end-to-end machine learning workflows powered by distributed computing framework like Ray, enabling scalable and efficient ML systems. Suman’s expertise spans Natural Language Processing (NLP), Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG). Earlier in his career, he developed performance benchmarking and monitoring tools for distributed storage systems. Beyond engineering, Suman is an active community contributor, having spoken at over 100 global conferences and events, including PyCon, PyData, ODSC, AIE and numerous meetups worldwide. Privacy-preserving in Computer Vision through Optics Learning Cameras are now ubiquitous, powering computer vision systems that assist us in everyday tasks and critical settings such as operating rooms. Yet, their widespread use raises serious privacy concerns: traditional cameras are designed to capture high-resolution images, making it easy to identify sensitive attributes such as faces, nudity, or personal objects. Once acquired, such data can be misused if accessed by adversaries. Existing software-based privacy mechanisms, such as blurring or pixelation, often degrade task performance and leave vulnerabilities in the processing pipeline. In this talk, we explore an alternative question: how can we preserve privacy before or during image acquisition? By revisiting the image formation model, we show how camera optics themselves can be learned and optimized to acquire images that are unintelligible to humans yet remain useful for downstream vision tasks like action recognition. We will discuss recent approaches to learning camera lenses that intentionally produce privacy-preserving images, blurry and unrecognizable to the human eye, but still effective for machine perception. This paradigm shift opens the door to a new generation of cameras that embed privacy directly into their hardware design. About the Speaker Carlos Hinojosa is a Postdoctoral researcher at King Abdullah University of Science and Technology (KAUST) working with Prof. Bernard Ghanem. His research interests span Computer Vision, Machine Learning, AI Safety, and AI for Science. He focuses on developing safe, accurate, and efficient vision systems and machine-learning models that can reliably perceive, understand, and act on information, while ensuring robustness, protecting privacy, and aligning with societal values. It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data Can we match vision and language embeddings without any supervision? According to the platonic representation hypothesis, as model and dataset scales increase, distances between corresponding representations are becoming similar in both embedding spaces. Our study demonstrates that pairwise distances are often sufficient to enable unsupervised matching, allowing vision-language correspondences to be discovered without any parallel data. About the Speaker Dominik Schnaus is a third-year Ph.D. student in the Computer Vision Group at the Technical University of Munich (TUM), supervised by Daniel Cremers. His research centers on multimodal and self-supervised learning with a special emphasis on understanding similarities across embedding spaces of different modalities. |
Oct 30 - AI, ML and Computer Vision Meetup
|
|
Aurélien Géron
– author
The potential of machine learning today is extraordinary, yet many aspiring developers and tech professionals find themselves daunted by its complexity. Whether you're looking to enhance your skill set and apply machine learning to real-world projects or are simply curious about how AI systems function, this book is your jumping-off place. With an approachable yet deeply informative style, author Aurélien Géron delivers the ultimate introductory guide to machine learning and deep learning. Drawing on the Hugging Face ecosystem, with a focus on clear explanations and real-world examples, the book takes you through cutting-edge tools like Scikit-Learn and PyTorch—from basic regression techniques to advanced neural networks. Whether you're a student, professional, or hobbyist, you'll gain the skills to build intelligent systems. Understand ML basics, including concepts like overfitting and hyperparameter tuning Complete an end-to-end ML project using scikit-Learn, covering everything from data exploration to model evaluation Learn techniques for unsupervised learning, such as clustering and anomaly detection Build advanced architectures like transformers and diffusion models with PyTorch Harness the power of pretrained models—including LLMs—and learn to fine-tune them Train autonomous agents using reinforcement learning |
O'Reilly AI & ML Books
|
|
Deep Learning with PyTorch
2025-10-28 · 15:30
Image Classification with PyTorch: ML Zoomcamp Module Update - Alexey Grigorev This is the fourth workshop in our ML series on ML model deployment and engineering. In the ML Zoomcamp course, our Deep Learning module has traditionally focused on TensorFlow and Keras. But PyTorch has rapidly become the dominant framework for deep learning. In this workshop, we’ll demonstrate how to implement key concepts, like convolutional neural networks, transfer learning, and training loops, using PyTorch. Led by Alexey Grigorev, this hands-on workshop demonstrates how to rewrite a TensorFlow/Keras project into PyTorch and train image classifiers. What you’ll learn:
By the end, you’ll have a working PyTorch training pipeline and an understanding of how it maps to the TensorFlow/Keras version. Like the other workshops, this will be a live demo with practical tips and time for Q&A. Thinking About ML Zoomcamp? This workshop reflects the updated Deep Learning module (Module 8) in the ML Zoomcamp. You’ll get a preview of how the course now includes both TensorFlow and PyTorch, so you can choose the framework that fits your workflow. ML Zoomcamp is our free 4-month course that takes you from beginner to advanced ML engineer. It covers the fundamentals of ML, from regression and classification to deployment and deep learning. The new cohort of the ML Zoomcamp starts on September 15, 2025. You can join it by registering here. About the Speaker Alexey Grigorev is the Founder of DataTalks.Club and creator of the Zoomcamp series. Alexey is a seasoned software and ML engineer with over 10 years in engineering and 6+ years in machine learning. He has deployed large-scale ML systems at companies like OLX Group and Simplaex, authored several technical books including Machine Learning Bookcamp, and is a Kaggle Master with a 1st place finish in the NIPS'17 Criteo Challenge. Join our slack: https://datatalks.club/slack.html |
Deep Learning with PyTorch
|
|
https://www.nvidia.com/en-eu/training/instructor-led-workshops/fundamentals-of-deep-learning/ Deep Learning with PyTorch Workshop In this workshop, you’ll learn how deep learning works through hands-on exercises in computer vision and natural language processing. You’ll train deep learning models from scratch, learning tools and tricks to achieve highly accurate results. You’ll also learn to leverage freely available, state-of-the-art pre-trained models to save time and get your deep learning application up and running quickly. Learning Objectives By participating in this workshop, you’ll:
Download workshop datasheet (PDF, 318 KB) Preparation for the Workshop
Mechanics of Deep Learning Explore the fundamental mechanics and tools involved in successfully training deep neural networks:
Pre-trained Models Leverage pre-trained models to solve deep learning challenges quickly. Train recurrent neural networks on sequential data:
Assessment Challenge: Image Classification Apply computer vision to create a model that distinguishes between fresh and rotten fruit:
Final Review
|
Fundamentals of Deep Learning: NVIDIA DLI Certification Workshop for Academia
|
|
https://www.nvidia.com/en-eu/training/instructor-led-workshops/fundamentals-of-deep-learning/ Deep Learning with PyTorch Workshop In this workshop, you’ll learn how deep learning works through hands-on exercises in computer vision and natural language processing. You’ll train deep learning models from scratch, learning tools and tricks to achieve highly accurate results. You’ll also learn to leverage freely available, state-of-the-art pre-trained models to save time and get your deep learning application up and running quickly. Learning Objectives By participating in this workshop, you’ll:
Download workshop datasheet (PDF, 318 KB) Preparation for the Workshop
Mechanics of Deep Learning Explore the fundamental mechanics and tools involved in successfully training deep neural networks:
Pre-trained Models Leverage pre-trained models to solve deep learning challenges quickly. Train recurrent neural networks on sequential data:
Assessment Challenge: Image Classification Apply computer vision to create a model that distinguishes between fresh and rotten fruit:
Final Review
|
Fundamentals of Deep Learning: NVIDIA DLI Certification Workshop for Academia
|
|
Deep Learning with Python, Third Edition
2025-09-24
Matthew Watson
– author
,
Francois Chollet
– author
The bestselling book on Python deep learning, now covering generative AI, Keras 3, PyTorch, and JAX! Deep Learning with Python, Third Edition puts the power of deep learning in your hands. This new edition includes the latest Keras and TensorFlow features, generative AI models, and added coverage of PyTorch and JAX. Learn directly from the creator of Keras and step confidently into the world of deep learning with Python. In Deep Learning with Python, Third Edition you’ll discover: Deep learning from first principles The latest features of Keras 3 A primer on JAX, PyTorch, and TensorFlow Image classification and image segmentation Time series forecasting Large Language models Text classification and machine translation Text and image generation—build your own GPT and diffusion models! Scaling and tuning models With over 100,000 copies sold, Deep Learning with Python makes it possible for developers, data scientists, and machine learning enthusiasts to put deep learning into action. In this expanded and updated third edition, Keras creator François Chollet offers insights for both novice and experienced machine learning practitioners. You'll master state-of-the-art deep learning tools and techniques, from the latest features of Keras 3 to building AI models that can generate text and images. About the Technology In less than a decade, deep learning has changed the world—twice. First, Python-based libraries like Keras, TensorFlow, and PyTorch elevated neural networks from lab experiments to high-performance production systems deployed at scale. And now, through Large Language Models and other generative AI tools, deep learning is again transforming business and society. In this new edition, Keras creator François Chollet invites you into this amazing subject in the fluid, mentoring style of a true insider. About the Book Deep Learning with Python, Third Edition makes the concepts behind deep learning and generative AI understandable and approachable. This complete rewrite of the bestselling original includes fresh chapters on transformers, building your own GPT-like LLM, and generating images with diffusion models. Each chapter introduces practical projects and code examples that build your understanding of deep learning, layer by layer. What's Inside Hands-on, code-first learning Comprehensive, from basics to generative AI Intuitive and easy math explanations Examples in Keras, PyTorch, JAX, and TensorFlow About the Reader For readers with intermediate Python skills. No previous experience with machine learning or linear algebra required. About the Authors François Chollet is the co-founder of Ndea and the creator of Keras. Matthew Watson is a software engineer at Google working on Gemini and a core maintainer of Keras. Quotes Perfect for anyone interested in learning by doing from one of the industry greats. - Anthony Goldbloom, Founder of Kaggle A sharp, deeply practical guide that teaches you how to think from first principles to build models that actually work. - Santiago Valdarrama, Founder of ml.school The most up-to-date and complete guide to deep learning you’ll find today! - Aran Komatsuzaki, EleutherAI Masterfully conveys the true essence of neural networks. A rare case in recent years of outstanding technical writing. - Salvatore Sanfilippo, Creator of Redis |
O'Reilly AI & ML Books
|
|
Building on PyTorch: Techniques for Extensibility and Innovation
2025-07-30 · 20:15
PyTorch has become the de facto standard for development and research in deep learning. Among the many factors contributing to its popularity is the wide array of customization hooks it provides. These extension mechanisms allow developers to build new functionality on top of PyTorch while maintaining compatibility with its core backend features—a powerful capability for engineers, researchers, and curious hackers, both in-core and downstream. In this talk, we’ll explore various ways to extend PyTorch and present concrete examples of these techniques in action. |
July Meetup: Building Better Workflows with Buckaroo & PyTorch
|
|
Zoom link: https://us02web.zoom.us/j/82308186562 Talk #0: Introductions and Meetup Updates by Chris Fregly and Antje Barth Talk #1: Building Accelerated PyTorch Operations with Mojo and the MAX runtime by Ehsan Kermani @ Modular (the Mojo folks) Ehsan will dive deep into the Mojo interfaces that enables developers to write PyTorch custom ops directly in Mojo. He’ll walk through how the interfaces work, show examples like a Mojo-accelerated Deep learning model such as Whisper and explain how this opens the door to integrating MAX and Mojo into existing PyTorch workflows. Talk #2: Dynamic and Adaptive AI Inference Serving Optimization Strategies with CUDA and vLLM by Chris Fregly, Author of AI Systems Performance Engineering Ultra-large language model (LLM) inference on modern hardware requires dynamic runtime adaptation to achieve both high throughput and low latency under varying conditions. A static “one-size-fits-all” approach to model-serving optimizations is no longer sufficient. Instead, state-of-the-art model serving systems use adaptive strategies that adjust parallelism, numerical precision, CUDA-kernel scheduling, and memory usage on the fly. This talk explores these advanced techniques including dynamic parallelism switching, precision scaling, real-time cache management, and reinforcement learning (RL)-based tuning. By the end of this talk, you will understand best practices for ultra-scale LLM inference. You will learn how to orchestrate an inference engine that monitors its own performance and adapts in real time to maximize efficiency. Zoom link: https://us02web.zoom.us/j/82308186562 Related Links Github Repo: http://github.com/cfregly/ai-performance-engineering/ O'Reilly Book: https://www.amazon.com/Systems-Performance-Engineering-Optimizing-Algorithms/dp/B0F47689K8/ YouTube: https://www.youtube.com/@AIPerformanceEngineering Generative AI Free Course on DeepLearning.ai: https://bit.ly/gllm |
Dynamic/Adaptive RL-based Inference Tuning + Accelerated PyTorch with Mojo/MAX
|
|
Zoom link: https://us02web.zoom.us/j/82308186562 Talk #0: Introductions and Meetup Updates by Chris Fregly and Antje Barth Talk #1: Building Accelerated PyTorch Operations with Mojo and the MAX runtime by Ehsan Kermani @ Modular (the Mojo folks) Ehsan will dive deep into the Mojo interfaces that enables developers to write PyTorch custom ops directly in Mojo. He’ll walk through how the interfaces work, show examples like a Mojo-accelerated Deep learning model such as Whisper and explain how this opens the door to integrating MAX and Mojo into existing PyTorch workflows. Talk #2: Dynamic and Adaptive AI Inference Serving Optimization Strategies with CUDA and vLLM by Chris Fregly, Author of AI Systems Performance Engineering Ultra-large language model (LLM) inference on modern hardware requires dynamic runtime adaptation to achieve both high throughput and low latency under varying conditions. A static “one-size-fits-all” approach to model-serving optimizations is no longer sufficient. Instead, state-of-the-art model serving systems use adaptive strategies that adjust parallelism, numerical precision, CUDA-kernel scheduling, and memory usage on the fly. This talk explores these advanced techniques including dynamic parallelism switching, precision scaling, real-time cache management, and reinforcement learning (RL)-based tuning. By the end of this talk, you will understand best practices for ultra-scale LLM inference. You will learn how to orchestrate an inference engine that monitors its own performance and adapts in real time to maximize efficiency. Zoom link: https://us02web.zoom.us/j/82308186562 Related Links Github Repo: http://github.com/cfregly/ai-performance-engineering/ O'Reilly Book: https://www.amazon.com/Systems-Performance-Engineering-Optimizing-Algorithms/dp/B0F47689K8/ YouTube: https://www.youtube.com/@AIPerformanceEngineering Generative AI Free Course on DeepLearning.ai: https://bit.ly/gllm |
Dynamic/Adaptive RL-based Inference Tuning + Accelerated PyTorch with Mojo/MAX
|
|
Zoom link: https://us02web.zoom.us/j/82308186562 Talk #0: Introductions and Meetup Updates by Chris Fregly and Antje Barth Talk #1: Building Accelerated PyTorch Operations with Mojo and the MAX runtime by Ehsan Kermani @ Modular (the Mojo folks) Ehsan will dive deep into the Mojo interfaces that enables developers to write PyTorch custom ops directly in Mojo. He’ll walk through how the interfaces work, show examples like a Mojo-accelerated Deep learning model such as Whisper and explain how this opens the door to integrating MAX and Mojo into existing PyTorch workflows. Talk #2: Dynamic and Adaptive AI Inference Serving Optimization Strategies with CUDA and vLLM by Chris Fregly, Author of AI Systems Performance Engineering Ultra-large language model (LLM) inference on modern hardware requires dynamic runtime adaptation to achieve both high throughput and low latency under varying conditions. A static “one-size-fits-all” approach to model-serving optimizations is no longer sufficient. Instead, state-of-the-art model serving systems use adaptive strategies that adjust parallelism, numerical precision, CUDA-kernel scheduling, and memory usage on the fly. This talk explores these advanced techniques including dynamic parallelism switching, precision scaling, real-time cache management, and reinforcement learning (RL)-based tuning. By the end of this talk, you will understand best practices for ultra-scale LLM inference. You will learn how to orchestrate an inference engine that monitors its own performance and adapts in real time to maximize efficiency. Zoom link: https://us02web.zoom.us/j/82308186562 Related Links Github Repo: http://github.com/cfregly/ai-performance-engineering/ O'Reilly Book: https://www.amazon.com/Systems-Performance-Engineering-Optimizing-Algorithms/dp/B0F47689K8/ YouTube: https://www.youtube.com/@AIPerformanceEngineering Generative AI Free Course on DeepLearning.ai: https://bit.ly/gllm |
Dynamic/Adaptive RL-based Inference Tuning + Accelerated PyTorch with Mojo/MAX
|
|
Simplifying Training and GenAI Finetuning Using Serverless GPU Compute
2025-06-10 · 17:20
Tejas Sundaresan
– Sr. Product Manager
@ Databricks
The last year has seen the rapid progress of Open Source GenAI models and frameworks. This talk covers best practices for custom training and OSS GenAI finetuning on Databricks, powered by the newly announced Serverless GPU Compute. We’ll cover how to use Serverless GPU compute to power AI training/GenAI finetuning workloads and framework support for libraries like LLM Foundry, Composer, HuggingFace, and more. Lastly, we’ll cover how to leverage MLFlow and the Databricks Lakehouse to streamline the end to end development of these models. Key takeaways include: How Serverless GPU compute saves customers valuable developer time and overhead when dealing with GPU infrastructure Best practices for training custom deep learning models (forecasting, recommendation, personalization) and finetuning OSS GenAI Models on GPUs across the Databricks stack Leveraging distributed GPU training frameworks (e.g. Pytorch, Huggingface) on Databricks Streamlining the path to production for these models Join us to learn about the newly announced Serverless GPU Compute and the latest updates to GPU training and finetuning on Databricks! |
Data + AI Summit 2025 |
|
From Trees to Transformers: Our Journey Towards Deep Learning for Ranking
2025-06-08 · 09:15
GetYourGuide, a global marketplace for travel experiences, reached diminishing returns with its XGBoost-based ranking system. We switched to a Deep Learning pipeline in just nine months, maintaining high throughput and low latency. We iterated on over 50 offline models and conducted more than 10 live A/B tests, ultimately deploying a PyTorch transformer that yielded significant gains. In this talk, we will share our phased approach—from a simple baseline to a high-impact launch—and discuss the key operational and modeling challenges we faced. Learn how to transition from tree-based methods to neural networks and unlock new possibilities for real-time ranking. |
PyData London 2025 |
|
May 20 - Image Generation: Diffusion Models & U-Net Workshop
2025-05-20 · 16:30
When and Where
About the Workshop Join us for a 12-part, hands-on series that teaches you how to work with images, build and train models, and explore tasks like image classification, segmentation, object detection, and image generation. Each session combines straightforward explanations with practical coding in PyTorch and FiftyOne, allowing you to learn core skills in computer vision and apply them to real-world tasks. In this session, we’ll explore image generation techniques using diffusion models. Participants will build a U-Net-based model to generate MNIST-like images and then inspect the generated outputs with FiftyOne. These are hands-on maker workshops that make use of GitHub Codespaces, Kaggle notebooks, and Google Colab environments, so no local installation is required (though you are welcome to work locally if preferred!) Workshop Resources You can find the workshop materials in this GitHub repository. About the Instructor Antonio Rueda-Toicen, an AI Engineer in Berlin, has extensive experience in deploying machine learning models and has taught over 300 professionals. He is currently a Research Scientist at the Hasso Plattner Institute. Since 2019, he has organized the Berlin Computer Vision Group and taught at Berlin’s Data Science Retreat. He specializes in computer vision, cloud technologies, and machine learning. Antonio is also a certified instructor of deep learning and diffusion models in NVIDIA’s Deep Learning Institute. |
May 20 - Image Generation: Diffusion Models & U-Net Workshop
|