119 citations · 468 across the 54 of their papers we have counts for
4 papers · 2 filters
Interpreting Neural Networks through the Polytope Lens
Sid Black, Lee Sharkey, Leo Grinsztajn +8
Mechanistic interpretability aims to explain what a neural network has learned at a nuts-and-bolts level. What are the fundamental primitives of neural network representations? Pre…
Predictive Coding beyond Gaussian Distributions
Luca Pinchetti, Tommaso Salvatori, Yordan Yordanov +3
A large amount of recent research has the far-reaching goal of finding training methods for deep neural networks that can serve as alternatives to backpropagation (BP). A prominent…
Backpropagation at the Infinitesimal Inference Limit of Energy-Based Models: Unifying Predictive Coding, Equilibrium Propagation, and Contrastive Hebbian Learning
Beren Millidge, Yuhang Song, Tommaso Salvatori +2
How the brain performs credit assignment is a fundamental unsolved problem in neuroscience. Many `biologically plausible' algorithms have been proposed, which compute gradients tha…
Learning on Arbitrary Graph Topologies via Predictive Coding
Tommaso Salvatori, Luca Pinchetti, Beren Millidge +4
Training with backpropagation (BP) in standard deep learning consists of two main steps: a forward pass that maps a data point to its prediction, and a backward pass that propagate…