Training Neural Networks with Local Error Signals

Abstract

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 gradient is back-propagated to hidden layers to dictate an update direction for the weights. An alternative approach is to train the network with layer-wise loss functions. In this paper we demonstrate, for the first time, that layer-wise training can approach the state-of-the-art on a variety of image datasets. 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. Using local errors could be a step towards more biologically plausible deep learning because the global error does not have to be transported back to hidden layers. A completely backprop free variant outperforms previously reported results among methods aiming for higher biological plausibility. Code is available https://github.com/anokland/local-loss

Accepted to ICML 2019

Cited by in corpus (15)

• Drawing Inspiration from Biological Dendrites to Empower Artificial Neural Networks
• Deep Learning Theory Review: An Optimal Control and Dynamical Systems Perspective
• Revisiting Locally Supervised Learning: an Alternative to End-to-end Training
• Predictive Coding Can Do Exact Backpropagation on Convolutional and Recurrent Neural Networks
• Hardware Beyond Backpropagation: a Photonic Co-Processor for Direct Feedback Alignment
• Convex Regularization Behind Neural Reconstruction
• Credit Assignment Through Broadcasting a Global Error Vector
• Learning to Time-Decode in Spiking Neural Networks Through the Information Bottleneck
• Learning in Deep Neural Networks Using a Biologically Inspired Optimizer
• Signature-Graph Networks
• Intra-Model Collaborative Learning of Neural Networks
• Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers
• Accumulated Decoupled Learning: Mitigating Gradient Staleness in Inter-Layer Model Parallelization
• On-Chip Error-triggered Learning of Multi-layer Memristive Spiking Neural Networks
• Front Contribution instead of Back Propagation