Search Results for author:
Found 4 papers, 4 papers with code
Training Neural Networks with Local Error Signals
We use single-layer sub-networks and two different supervised loss functions to generate local error signals for the hidden layers, and we show that the combination of these losses help with optimization in the context of local learning.
Ranked #3 on
Image Classification
on Kuzushiji-MNIST
Shifting Mean Activation Towards Zero with Bipolar Activation Functions
We explore the training of deep vanilla recurrent neural networks (RNNs) with up to 144 layers, and show that bipolar activation functions help learning in this setting.
Direct Feedback Alignment Provides Learning in Deep Neural Networks
In this work, the feedback alignment principle is used for training hidden layers more independently from the rest of the network, and from a zero initial condition.
Improving Back-Propagation by Adding an Adversarial Gradient
The first experimental results on MNIST show that the "adversarial back-propagation" method increases the resistance to adversarial examples and boosts the classification performance.
