Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Rescuing Points Trapped Inside Incorrect Decision Regions: A target for Evaluating and Improving Forward-Forward Learning
Alireza Rahmansetayesh, Amirhossein Yousefiramandi, Maxwell Spiridonov +3
Forward-Forward learning replaces end-to-end backpropagation with local, layer-wise training objectives. Its variants are evaluated primarily by classification accuracy, often meas…
cs.LG2026
Layer-wise Input Recoverability in Deep Neural Networks
Maxwell Spiridonov, Alireza Rahmansetayesh, Pierre Baldi
The inner workings of deep neural networks are still not well understood. The information bottleneck framework, which characterizes deep networks by the mutual information between…