← Search

Jonathan Bloom

2 accepted papers

2020

Two Routes to Scalable Credit Assignment without Weight Symmetry

ICML 2020poster

The neural plausibility of backpropagation has long been disputed, primarily for its use of non-local weight transport — the biologically dubious requirement that one neuron instantaneously measure the synaptic weights of another. Until recently, attempts to create local learning rules that avoid we…

2019

Loss Landscapes of Regularized Linear Autoencoders

ICML 2019oral

Autoencoders are a deep learning model for representation learning. When trained to minimize the distance between the data and its reconstruction, linear autoencoders (LAEs) learn the subspace spanned by the top principal directions but cannot learn the principal directions themselves. In this paper…