论文标题
元学习在生物学上具有随机反馈途径的可靠性规则
Meta-Learning Biologically Plausible Plasticity Rules with Random Feedback Pathways
论文作者
论文摘要
反向传播广泛用于训练人工神经网络，但其与大脑突触可塑性的关系尚不清楚。一些反向传播的生物学模型依赖于与前馈连接对称的反馈投影，但是实验并不能证实这种对称的向后连接的存在。随机反馈对齐提供了一种替代模型，其中错误通过固定的随机向后连接向后传播。这种方法成功地训练了浅模型，但学习缓慢，并且在更深层次的模型或在线学习方面表现不佳。在这项研究中，我们开发了一种元学习方法，以发现可解释的，生物学上合理的可塑性规则，从而通过固定的随机反馈连接来改善在线学习绩效。由此产生的可塑性规则显示了低数据制度中深层模型的在线培训得到了改进。我们的结果突出了元学习发现满足生物学约束的有效，可解释的学习规则的潜力。
Backpropagation is widely used to train artificial neural networks, but its relationship to synaptic plasticity in the brain is unknown. Some biological models of backpropagation rely on feedback projections that are symmetric with feedforward connections, but experiments do not corroborate the existence of such symmetric backward connectivity. Random feedback alignment offers an alternative model in which errors are propagated backward through fixed, random backward connections. This approach successfully trains shallow models, but learns slowly and does not perform well with deeper models or online learning. In this study, we develop a meta-learning approach to discover interpretable, biologically plausible plasticity rules that improve online learning performance with fixed random feedback connections. The resulting plasticity rules show improved online training of deep models in the low data regime. Our results highlight the potential of meta-learning to discover effective, interpretable learning rules satisfying biological constraints.
