180 citations · 339 across the 4 of their papers we have counts for
4 papers
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…
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…
Direct Feedback Alignment Provides Learning in Deep Neural Networks
Arild Nøkland
Artificial neural networks are most commonly trained with the back-propagation algorithm, where the gradient for learning is provided by back-propagating the error, layer by layer,…
Improving Back-Propagation by Adding an Adversarial Gradient
Arild Nøkland
The back-propagation algorithm is widely used for learning in artificial neural networks. A challenge in machine learning is to create models that generalize to new data samples no…