The impact of differentiable programming: how ∂P is enabling new science in Julia

Matt Bauman demonstrates how incorporating differentiable programming into Julia enables composability between machine learning and scientific simulation.

Fully incorporating differentiable programming (∂P) into the Julia language has enabled composability between modern machine learning techniques and existing high performance computing (HPC) modeling and simulation without sacrificing expressivity. Most notably, this has meant that small neural networks can be embedded within larger models whose other behaviors are fully understood and can be concretely represented. Smaller neural networks, in turn, are easier to train and interpret. It has also enabled complex computations to be embedded within cost functions for fast and robust reinforcement learning. In this talk, we’ll walk through several concrete examples and demonstrate how the combination of ∂P with Julia’s generic programming has enabled powerful and expressive new models. Presented by Matt Bauman