talk-data.com

PyData Pittsburgh is excited to host our first event of 2025: Machine Learning in Astronomy. Join us on Tuesday, February 25, as Ashod Khederlarian, a 4th-year Ph.D. student at the University of Pittsburgh, shares state-of-the-art Machine Learning techniques being used to analyze vast astronomical datasets.

We have an exciting venue for this event—the Allegheny Observatory has graciously agreed to not only host the talk but also offer a free private tour exclusively for the PyData Pittsburgh group after the presentation! Don’t miss this opportunity to learn about cutting-edge AI applications in astronomy while exploring one of Pittsburgh’s most fascinating scientific landmarks.

Note: Attendance for this event is limited. Please RSVP only if you are committed to attending. Thank you.

About the talk:

Astronomy is an observational science. To understand the history and evolution of our universe and everything in it, our only option is to observe the night sky and test our theories against the observations. Current and next-generation observatories, such as the Dark Energy Spectroscopic Instrument, the Rubin Observatory, the Roman Space Telescope, and the Euclid Space Telescope will collect light coming from billions of galaxies and stars, resulting in 10s of terabytes of data per night. Most of this complex, high-dimensional data will not be seen by the naked eye, making data science and Machine Learning (ML) tools essential for analyzing them.

In this talk, Ashod will highlight how state-of-the-art ML techniques are being used in Astronomy. Particularly, he will focus on his work at the University of Pittsburgh on using simple neural networks to add realistic properties to galaxy simulations, using deep convolutional neural networks to make 3D maps of the universe, and using dimensionality reduction techniques to visualize high-dimensional datasets.

About the observatory:

The Allegheny Observatory is one of the major historic astronomical research institutions of the world. A short presentation about the institution will be shown followed by a walking tour of the building finally ending up at the 13" Fitz-Clark refractor.

Times: 7pm, Doors Open 7:30pm, Machine Learning in Astronomy Talk 8:30pm, Observatory Tour

Getting to the observatory:

Address: 159 Riverview Ave, Pittsburgh, PA 15214

If you are coming up 279 from Pittsburgh, take exit 3, Hazlett St. Turn left on East street. Continue north on East St. DO NOT turn left on Milroy. Your mapping program will reroute you: Continue on and bear left to stay on East street at the 4th light. Make a sharp left turn onto Perrysville Ave. Continue on to make a right turn at Riverview Ave.

You can park on the righthand side of the one way road that loops around the observatory, or in the parking lot for the nearby dog park. Enter through the main doors and proceed to the event room.

If you arrive at the front door and it is closed, please knock or buzz the bell. Thanks!

To use a handicapped-accessible ramp, park in the back of the observatory, use the ramp to the back door and ring the doorbell to the left of the door.

Welcome to the PyData Berlin January meetup!

We would like to welcome you all starting from 18:45. There will be food and drinks. The talks begin around 19.30 and the doors will close at 19:30. Make sure to arrive on time!

Please provide your first and last name for the registration because this is required for the venue's entry policy. If you cannot attend, please cancel your spot so others are able to join as the space is limited.

Host: GetYourGuide is excited to welcome you to this month's version of PyData. ************************************************************************** The Lineup for the evening

Talk 1: Building Delivery Hero’s Product Semantic Similarity Using Real-Time Vector Search Abstract: Delivery Hero's Quick Commerce service offers a convenient way for customers to order items from grocery stores for delivery. However, the Marketplace has thousands of stores and millions of products. The company risks revenue loss and churn if Customers cannot easily find products that match their needs and preferences. In this talk, we will explore how Delivery Hero developed a Product Semantic Similarity recommender to identify Similar Products in multiple touchpoints of Customer's purchasing journey, by using Transformer-based product embeddings and Atlas Vector Search.

Speaker: Fahad Yousaf Bio: Hailing from Pakistan, I am a Machine Learning Engineer at Delivery Hero. My previous roles include working at i2c Inc., and Turing. Over the course of my career, I have developed and productionized a range of machine learning applications, such as Call Transcription Analytics powered by Natural Language Processing, Mobile Remote Deposit Cheque processing using Computer Vision, Semantic Search systems etc. Outside of work, I enjoy learning about the mysteries of the universe.

Talk 2: Introduction to the open-source world: It's all just a series of gifts! Abstract: The Python community is an incredibly welcome and diverse community, open to people from all backgrounds and of any experience level. With a vast variety of projects to get involved with, it can serve as your point of entry into the world of open-source software, whatever your interests might be. From PyGame for gamers interested in game engines to NumPy for data scientists and mathematicians, it's got something for everyone. In this talk, we'll set out on a journey through the different parts of the Python community and we'll use that to discuss ways to get started with open-source software, get a better idea of what makes a good contributor and hopefully give everyone a better picture of what to expect when getting into this very exciting world.

Speaker: Lysandros Nikolaou Bio: Lysandros works as a Senior Software Engineer at Quansight Labs. He is a CPython core developer, specializing in the parser, the tokenizer and the REPL. He recently worked on supercharging f-strings in Python 3.12, the new REPL for Python 3.13 and introducing fast string ufuncs in NumPy 2.0. Currently, he's mostly dealing with improving support for free-threaded Python in the PyData ecosystem.

Lightning talks There will be slots for 2-3 Lightning Talks (3-5 Minutes for each) between the two main talks. Kindly let us know if you would like to present something :)

*** NumFOCUS Code of Conduct THE SHORT VERSION Be kind to others. Do not insult or put down others. Behave professionally. Remember that harassment and sexist, racist, or exclusionary jokes are not appropriate for NumFOCUS. All communication should be appropriate for a professional audience including people of many different backgrounds. Sexual language and imagery are not appropriate. NumFOCUS is dedicated to providing a harassment-free community 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 community members in any form. Thank you for helping make this a welcoming, friendly community for all. If you haven't yet, please read the detailed version here: https://numfocus.org/code-of-conduct ***