131 citations · 140 across the 2 of their papers we have counts for
Showing stat.MLShow all
2 papers · 1 filter
stat.ML2019★ 131 cited
Training Neural Networks with Local Error Signals
Arild Nøkland, Lars Hiller Eidnes
Supervised training of neural networks for classification is typically performed with a global loss function. The loss function provides a gradient for the output layer, and this g…
stat.ML2017★ 9 cited
Shifting Mean Activation Towards Zero with Bipolar Activation Functions
Lars Eidnes, Arild Nøkland
We propose a simple extension to the ReLU-family of activation functions that allows them to shift the mean activation across a layer towards zero. Combined with proper weight init…