An HSIC-based information-bottleneck objective trains deep networks layer-by-layer without backpropagation and matches backpropagation accuracy on small image benchmarks in the reported runs.
A.; Fischer, I.; Dillon, J
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The HSIC Bottleneck: Deep Learning without Back-Propagation
An HSIC-based information-bottleneck objective trains deep networks layer-by-layer without backpropagation and matches backpropagation accuracy on small image benchmarks in the reported runs.