research
∙
01/20/2019
Training Neural Networks with Local Error Signals
Supervised training of neural networks for classification is typically p...
share
research
∙
09/12/2017
Shifting Mean Activation Towards Zero with Bipolar Activation Functions
We propose a simple extension to the ReLU-family of activation functions...
research
∙
09/06/2016
Direct Feedback Alignment Provides Learning in Deep Neural Networks
Artificial neural networks are most commonly trained with the back-propa...
research
∙
10/14/2015
