Training Very Deep Networks

NeurIPS 2015 Rupesh Kumar SrivastavaKlaus GreffJürgen Schmidhuber

Theoretical and empirical evidence indicates that the depth of neural networks is crucial for their success. However, training becomes more difficult as depth increases, and training of very deep networks remains an open problem... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Classification CIFAR-10 VDN Percentage correct 92.4 # 55
Percentage error 7.60 # 28
Image Classification CIFAR-100 VDN Percentage correct 67.8 # 55
Percentage error 32.34 # 22
Image Classification MNIST VDN Percentage error 0.5 # 13

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet