Deep Learning

4 talks from the 2023 edition.

Getting started with JAX ▶ Recording 📝 Transcript

Simon Pressler

Deepminds JAX ecosystem provides deep learning practitioners with an appealing alternative to TensorFlow and PyTorch. Among its strengths are great functionalities such as native TPU support, as well as easy...
Honey, I broke the PyTorch model >.< - Debugging custom PyTorch models in a structured manner

Clara Hoffmann

When building PyTorch models for custom applications from scratch there's usually one problem: The model does not learn anything. In a complex project, it can be tricky to identify the cause: Is it the data? A bug in...
Teaching Neural Networks a Sense of Geometry ▶ Recording 📝 Transcript

Jens Agerberg

By taking neural networks back to the school bench and teaching them some elements of geometry and topology we can build algorithms that can reason about the shape of data. Surprisingly these methods can be useful...
Why GPU Clusters Don't Need to Go Brrr? Leverage Compound Sparsity to Achieve the Fastest Inference Performance on CPUs

Damian Bogunowicz

Forget specialized hardware. Get GPU-class performance on your commodity CPUs with compound sparsity and sparsity-aware inference execution. This talk will demonstrate the power of compound sparsity for model...