Drawing Inspiration from Biological Dendrites to Empower Artificial Neural Networks
arXiv:2106.07490 · doi:10.1016/j.conb.2021.04.007
Abstract
This article highlights specific features of biological neurons and their dendritic trees, whose adoption may help advance artificial neural networks used in various machine learning applications. Advancements could take the form of increased computational capabilities and/or reduced power consumption. Proposed features include dendritic anatomy, dendritic nonlinearities, and compartmentalized plasticity rules, all of which shape learning and information processing in biological networks. We discuss the computational benefits provided by these features in biological neurons and suggest ways to adopt them in artificial neurons in order to exploit the respective benefits in machine learning.
12 pages, 1 figure, opinion article
References in corpus (6)
- Training Neural Networks with Local Error Signals
- Biologically plausible deep learning -- but how far can we go with shallow networks?
- On the Impact of the Activation Function on Deep Neural Networks Training
- Liquid State Machine with Dendritically Enhanced Readout for Low-power, Neuromorphic VLSI Implementations
- Can Single Neurons Solve MNIST? The Computational Power of Biological Dendritic Trees
- Continual Learning with Deep Artificial Neurons