PyTorch Foundation with Ibrahim Haddad

Hi everyone, good afternoon. I hope you’re having a great conference today. My name is Ibrahim Hadad and I’m the Executive Director of the LFAI and Data Foundation. As recently as September, the Pytorch Foundation as well. I work for the Linux Foundation in support of the Pytorch Foundation and I have here with me […]

#97 SREEJAN KUMAR – Human Inductive Biases in Machines from Language

Research has shown that humans possess strong inductive biases which enable them to quickly learn and generalize. Now in order to instill the same useful inductive biases into machines, a paper was presented by Sri Jankuma at the New Ups Conference and it won the Outstanding Paper of the Year Award. Now the paper is […]

Two Minute Papers: New AI Makes Amazing DeepFakes In a Blink of an Eye!

Dear Fellow Scholars, this is Two Minute Papers with Dr. Karojone Fahid. Today we are going to transform ourselves into cartoon characters, and it is going to be amazing. But how? Well, for instance, let’s start out from Style Transfer. Style Transfer means mixing two images together, one for content, reimagined with the other one […]

Reinforcement Learning for Personalization at Spotify with Tony Jebara – 609

All right, everyone. Welcome to another episode of the Twilmo AI podcast. I am your host, Sam Charrington. And today I’m joined by Tony Jabara. Tony is a vice president of engineering and head of machine learning at Spotify. Before we get going, be sure to take a moment to hit that subscribe button wherever […]

SingularityNET: Inside SingularityNET | December 2022

Good morning, good evening, good night, good wherever you are around the world tuning in to December’s edition of Singularity Net Insiders. It’s wonderful to do this recording for you, it’s fantastic to generally get together and celebrate all our enormous achievements of 2022 with a little look forward to 2023. Thank you as always […]

PyTorch Mobile on Android using C++ (PyTorch Conference 2022 Breakout Session)

Yeah, my name is Joe Bowser. I’m with Adobe. We’re going to talk today about our explorations and using PyTorch mobile on Android. We’re using C++. I’m with the Sensei on device team, our Sensei ML and Furns and efficiency team at Adobe. We go across teams and work on features. So just to give […]

FSDP Production Readiness

Hi, everyone, and welcome to the PyTorch conference. My name is Rohan, and today we’ll be discussing the fully-sharded data parallel package in PyTorch, and in particular some of the work we’ve been doing to ensure it’s ready for production quality training of large models. First, we’ll go over some motivation regarding why we need […]