Abstract
AbstractFor both humans and machines, the essence of learning is to pinpoint which components in its information processing pipeline are responsible for an error in its output, a challenge that is known as ‘credit assignment’. It has long been assumed that credit assignment is best solved by backpropagation, which is also the foundation of modern machine learning. Here, we set out a fundamentally different principle on credit assignment called ‘prospective configuration’. In prospective configuration, the network first infers the pattern of neural activity that should result from learning, and then the synaptic weights are modified to consolidate the change in neural activity. We demonstrate that this distinct mechanism, in contrast to backpropagation, (1) underlies learning in a well-established family of models of cortical circuits, (2) enables learning that is more efficient and effective in many contexts faced by biological organisms and (3) reproduces surprising patterns of neural activity and behavior observed in diverse human and rat learning experiments.
Publisher
Springer Science and Business Media LLC
Reference80 articles.
1. Lillicrap, T. P., Santoro, A., Marris, L., Akerman, C. J. & Hinton, G. Backpropagation and the brain. Nat. Rev. Neurosci. 21, 335–346 (2020).
2. Rumelhart, D. E., Hinton, G. E. & Williams, R. J. Learning Internal Representations by Error Propagation (Univ. California, San Diego, Institute for Cognitive Science, 1985).
3. Krizhevsky, A., Sutskever, I. & Hinton, G. E. ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems (NeurIPS) (eds Bartlett, P. et al.) 1097–1105 (Curran Associates, 2012).
4. Mnih, V. et al. Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015).
5. Silver, D. et al. Mastering the game of go with deep neural networks and tree search. Nature 529, 484–489 (2016).
Cited by
11 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献