逆传播
一、人工神经网络中的反向传播(对比基础)编辑本段
二、生物神经系统的潜在"逆传播"机制编辑本段
生物神经元的学习依赖突触可塑性(如Hebbian学习规则:"一起激发的神经元连接加强")。但反向传播的全局优化特性在生物脑中如何实现仍是未解之谜。目前主要有三类假说:
ADSFAEQWER353423413434
1. 反馈连接与误差信号传递
- 解剖基础:
- 可能的误差传递:
2. 脉冲时序依赖可塑性(STDP)的类反向传播
- STDP机制:突触前后神经元脉冲的时序决定突触增强(LTP)或减弱(LTD)。
- 潜在反向传播模拟:
- 若输出层神经元在目标信号后激发(表示误差),其反馈脉冲可能与输入脉冲形成特定时序关系,诱发突触调整。
- 局限性:STDP本质是局部规则,难以解释多层网络的全局优化。
3. 神经调制物质的"广播式"误差信号
三、关键争议与挑战编辑本段
四、前沿进展:生物学更合理的替代方案编辑本段
总结编辑本段
参考资料编辑本段
- Lillicrap, T. P., Santoro, A., Marris, L., Akerman, C. J., & Hinton, G. (2020). Backpropagation and the brain. Nature Reviews Neuroscience, 21(6), 335-346.
- Whittington, J. C. R., & Bogacz, R. (2019). Theories of error back-propagation in the brain. Trends in Cognitive Sciences, 23(3), 235-250.
- Rao, R. P. N., & Ballard, D. H. (1999). Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects. Nature Neuroscience, 2(1), 79-87.
- Scellier, B., & Bengio, Y. (2017). Equilibrium propagation: bridging the gap between energy-based models and backpropagation. Frontiers in Computational Neuroscience, 11, 24.
- Lee, D. H., Zhang, S., Fischer, A., & Bengio, Y. (2015). Difference target propagation. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases (pp. 498-515). Springer.
- Song, S., Miller, K. D., & Abbott, L. F. (2000). Competitive Hebbian learning through spike-timing-dependent synaptic plasticity. Nature Neuroscience, 3(9), 919-926.
- Schultz, W., Dayan, P., & Montague, P. R. (1997). A neural substrate of prediction and reward. Science, 275(5306), 1593-1599.
- Hinton, G. E. (2022). The forward-forward algorithm: Some preliminary investigations. arXiv preprint arXiv:2212.13345.
- Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533-536.
- Friston, K. (2010). The free-energy principle: a unified brain theory? Nature Reviews Neuroscience, 11(2), 127-138.
附件列表
词条内容仅供参考,如果您需要解决具体问题
(尤其在法律、医学等领域),建议您咨询相关领域专业人士。
