Search – talk-data.com

Title & Speakers	Event
PyData Cambridge - 53rd Meetup 2024-05-15 · 18:00 Agenda 📣📣We are happy to announce the 53rd PyData Cambridge meetup!📣📣 Agenda: 18:45 - 🚪 Doors open (Please do not arrive earlier) 19:00 - ▶️ Introduction 19:15 - 🗣 Image Registration: How to align images, by Mayank Patwari, Astra Zeneca. 19:50 - 🍕 Interval - pizza and drinks provided 20:15 - 🗣Data-driven optimization for expensive problems: a chemical reactor case study, by Antonio del Rio Chanona, Imperial College London. 20:50 - 🍻 End (Pub - Station Tavern, Station Square, map here). This event is sponsored by the Raspberry Pi Foundation. ---------------------------------------------------------------- Abstracts Image Registration: How to align images, by Mayank Patwari Image registration, the process of aligning two images with identical or overlapping content, is a ubiquitous challenge in various domains today. From seamlessly stitching together images to craft panoramic views to capturing objects in 3D through scanning, the applications of image registration are manifold and impactful. This talk will delve into the fundamental mathematical principles and essential methodologies underpinning image registration techniques. Moreover, it will explore compelling real-world applications, showcasing the diverse range of scenarios where image registration plays a pivotal role. Data-driven optimization for expensive problems: a chemical reactor case study Antonio del Rio Chanona The rise of digitalization, including smart measuring devices, analytical technology, sensor technologies, cloud platforms, and the Industrial Internet of Things (IIoT), has led to the emergence of data-driven optimization. Optimization algorithms that are guided purely by collected data are now in high demand. In this talk, we will discuss Bayesian optimization, a data-driven optimization algorithm, and its application to solving "expensive" optimization problems. Expensive data-driven optimization problems are those with high costs, such as neural network hyperparameter tuning, expensive computer simulations, and chemical experiments. These costs can be computational time, monetary, or any other budget. Our focus will be on the design of chemical reactors coupled with computational fluid dynamics simulations and their manufacturability via 3D printing. We will explore how Bayesian optimization can be used to optimize chemical reactor design and improve their performance while reducing costs. By leveraging data-driven optimization algorithms, we can achieve more efficient and sustainable chemical processes. This talk will provide insights into the potential of Bayesian optimization for engineering systems. ---------------------------------------------------------------- Speakers Bios Mayank is a dedicated scientist with a diverse skill set encompassing computer vision, biomedical engineering, machine learning, and medical physics. He earned his Master's degree in Biomedical Computing from TU Munich and completed his Bachelor's degree at the University of Hong Kong. Mayank's research primarily focuses on machine learning applications in computer vision and medical imaging, resulting in several noteworthy publications. One of his papers was recognized as among the top 10% most read papers in the years 2023-2024 by the prestigious journal Medical Physics, highlighting his contributions to the field. Antonio del Rio Chanona is head of the Optimisation and Machine Learning for Process Systems Engineering group at the Department of Chemical Engineering, Imperial College London. Antonio received his MEng from UNAM in Mexico, and his PhD from the University of Cambridge where he was awarded the Danckwerts-Pergamon Prize for the best doctoral thesis of his year. Antonio’s main research interests include Data-Driven Optimisation, Reinforcement Learning, Control and Hybrid Modelling applied to process systems engineering. ---------------------------------------------------------------- Code of Conduct PyData is dedicated to providing a harassment-free event experience for everyone, regardless of gender, sexual orientation, gender identity, and expression, disability, physical appearance, body size, race, or religion. We do not tolerate harassment of participants in any form. The PyData Code of Conduct governs this meetup. ( http://pydata.org/code-of-conduct.html ) To discuss any issues or concerns relating to the code of conduct or the behaviour of anyone at a PyData meetup, please contact NumFOCUS Executive Director Leah Silen ([email protected]) or organizers.	PyData Cambridge - 53rd Meetup

Agenda 📣📣We are happy to announce the 53rd PyData Cambridge meetup!📣📣 Agenda: 18:45 - 🚪 Doors open (Please do not arrive earlier) 19:00 - ▶️ Introduction 19:15 - 🗣 Image Registration: How to align images, by Mayank Patwari, Astra Zeneca. 19:50 - 🍕 Interval - pizza and drinks provided 20:15 - 🗣Data-driven optimization for expensive problems: a chemical reactor case study, by Antonio del Rio Chanona, Imperial College London. 20:50 - 🍻 End (Pub - Station Tavern, Station Square, map here).

This event is sponsored by the Raspberry Pi Foundation. ----------------------------------------------------------------

Abstracts

Image Registration: How to align images, by Mayank Patwari Image registration, the process of aligning two images with identical or overlapping content, is a ubiquitous challenge in various domains today. From seamlessly stitching together images to craft panoramic views to capturing objects in 3D through scanning, the applications of image registration are manifold and impactful. This talk will delve into the fundamental mathematical principles and essential methodologies underpinning image registration techniques. Moreover, it will explore compelling real-world applications, showcasing the diverse range of scenarios where image registration plays a pivotal role.

Data-driven optimization for expensive problems: a chemical reactor case study Antonio del Rio Chanona The rise of digitalization, including smart measuring devices, analytical technology, sensor technologies, cloud platforms, and the Industrial Internet of Things (IIoT), has led to the emergence of data-driven optimization. Optimization algorithms that are guided purely by collected data are now in high demand. In this talk, we will discuss Bayesian optimization, a data-driven optimization algorithm, and its application to solving "expensive" optimization problems.

Expensive data-driven optimization problems are those with high costs, such as neural network hyperparameter tuning, expensive computer simulations, and chemical experiments. These costs can be computational time, monetary, or any other budget. Our focus will be on the design of chemical reactors coupled with computational fluid dynamics simulations and their manufacturability via 3D printing.

We will explore how Bayesian optimization can be used to optimize chemical reactor design and improve their performance while reducing costs. By leveraging data-driven optimization algorithms, we can achieve more efficient and sustainable chemical processes. This talk will provide insights into the potential of Bayesian optimization for engineering systems.

----------------------------------------------------------------

Speakers Bios

Mayank is a dedicated scientist with a diverse skill set encompassing computer vision, biomedical engineering, machine learning, and medical physics. He earned his Master's degree in Biomedical Computing from TU Munich and completed his Bachelor's degree at the University of Hong Kong. Mayank's research primarily focuses on machine learning applications in computer vision and medical imaging, resulting in several noteworthy publications. One of his papers was recognized as among the top 10% most read papers in the years 2023-2024 by the prestigious journal Medical Physics, highlighting his contributions to the field.

Antonio del Rio Chanona is head of the Optimisation and Machine Learning for Process Systems Engineering group at the Department of Chemical Engineering, Imperial College London.

Antonio received his MEng from UNAM in Mexico, and his PhD from the University of Cambridge where he was awarded the Danckwerts-Pergamon Prize for the best doctoral thesis of his year. Antonio’s main research interests include Data-Driven Optimisation, Reinforcement Learning, Control and Hybrid Modelling applied to process systems engineering. ----------------------------------------------------------------

Code of Conduct PyData is dedicated to providing a harassment-free event experience for everyone, regardless of gender, sexual orientation, gender identity, and expression, disability, physical appearance, body size, race, or religion. We do not tolerate harassment of participants in any form. The PyData Code of Conduct governs this meetup. ( http://pydata.org/code-of-conduct.html ) To discuss any issues or concerns relating to the code of conduct or the behaviour of anyone at a PyData meetup, please contact NumFOCUS Executive Director Leah Silen ([email protected]) or organizers.

Activities & events