Upcoming Events

Loading Events

« All Events

  • This event has passed.

LIVE STREAM Talk with Adam Paszke, Co-Author of PyTorch: “PyTorch: A Modern Library for Machine Learning”

21st November 2019 @ 5:00 pm - 6:00 pm

ACM Tech talk are hosting a live talk on “PyTorch: A Modern Library for Machine Learning”,
It will take place at 17.00pm our time on 21st Novemeber if anyone is interested the ACM Chapter will be happy to accommodate streaming it from the college.
Please reply to this email to express your interest so we can get an idea of numbers.

November 21 Talk with Adam Paszke, Co-Author of PyTorch: “PyTorch: A Modern Library for Machine Learning”

to view image click on Register now for the next free ACM TechTalk, “PyTorch: A Modern Library for Machine Learning,” presented onThursday, November 21 at 12:00 PM ET/9:00 AM PT by Adam Paszke, co-author and maintainer of PyTorch. Erik Meijer, Director of Engineering at Facebook, Founder and CEO of Applied Duality, and member of the ACM Queue Editorial Board, will moderate the questions and answers session following the talk.

Leave your comments and questions with our speaker now and any time before the live event on ACM’s Discourse Page. And check out the page after the webcast for extended discussion with your peers in the computing community, as well as further resources on PyTorch.

(If you’d like to attend but can’t make it to the virtual event, you still need to register to receive a recording of the TechTalk when it becomes available.)

Note: You can stream this and all ACM TechTalks on your mobile device, including smartphones and tablets.

The recent explosion in the power and popularity of machine learning techniques has been fueled in part by the ecosystem of open source Python libraries. One of those was PyTorch, a successor to Torch7, which is rapidly becoming one of the most essential tools in every ML researcher’s toolbox.

However, research is not the end of the story. Machine learning is transforming entire fields, meaning that efficient inference is now becoming more important than ever. Even though PyTorch has strong roots in research applications, inference functionality is one of our recent focuses and has driven us to develop some innovative solutions in that space.

In this talk I will present the ideas underlying the library and how it can be utilized in the variety of scenarios in which machine learning appears, which range from research all the way to production.

Duration: 60 minutes (including audience Q&A)

Presenter:
Adam PaszkeCo-Author and Maintainer, PyTorch; University of Warsaw
Adam is an author and maintainer of PyTorch. He has already worked with large organizations like Facebook AI Research, Google, and NVIDIA, despite the fact that he has only recently graduated from the Master’s program in Computer Science at the University of Warsaw. Currently, he is also finishing his second major in Mathematics. His general interests include graph theory, programming languages, numerical computing, and machine learning.

Moderator:
Erik MeijerDirector of Engineering, Facebook; Founder and CEO, Applied Duality; ACM QueueEditorial Board
Erik Meijer is a Dutch computer scientist and entrepreneur. From 2000 to 2013 he was a software architect for Microsoft where he headed the Cloud Programmability Team. His work at Microsoft included C#, Visual Basic, LINQ, Volta, and the Reactive programming framework (Reactive Extensions) for .NET. His research has included the areas of functional programming (particularly Haskell) compiler implementation, parsing, programming language design, XML, and foreign function interfaces. In 2011, Erik was appointed part-time professor of Cloud Programming within the Software Engineering Research Group at Delft University of Technology. Since 2013 he is also an Honorary Professor of Programming Language Design at the School of Computer Science of the University of Nottingham, associated with the Functional Programming Laboratory.

Currently, Erik is CEO of Applied Duality Inc., which he founded in 2013. Since then he has worked on the Hack language with Facebook, RxJava library with Netflix, and Dart language with Google. In the past, he was an associate professor at Utrecht University. He received his Ph.D from Nijmegen University. Erik is the recipient of the Microsoft Outstanding Technical Leadership Award (2009) and the Outstanding Technical Achievement Award as a member of the C# team (2007). In October 2015, Erik joined Facebook to support the goal of Bono and Mark Zuckerberg to unite the world by connecting it. He teaches the “Principles of Reactive Programming” course through Coursera, and “Introduction to Functional Programming” through edX. He is also a member of theACM Queue Editorial Board.

Visit learning.acm.org/techtalks-archive for our full archive of past TechTalks.

Share With Your Colleagues

Details

Date:
21st November 2019
Time:
5:00 pm - 6:00 pm