Rapidly learning from ongoing experiences and remembering past events with a flexible memory system are two core capacities of biological intelligence. While the underlying neural mechanisms are not fully understood, various evidence supports that synaptic plasticity plays a critical role in memory formation and fast learning. Inspired by these results, we equip Recurrent Neural Networks (RNNs) with plasticity rules to enable them to adapt their parameters according to ongoing experiences. In addition to the traditional local Hebbian plasticity, we propose a global, gradient-based plasticity rule, which allows the model to evolve towards its self-determined target. Our models show promising results on sequential and associative memory tasks, illustrating their ability to robustly form and retain memories. In the meantime, these models can cope with many challenging few-shot learning problems. Comparing different plasticity rules under the same framework shows that Hebbian plasticity is well-suited for several memory and associative learning tasks; however, it is outperformed by gradient-based plasticity on few-shot regression tasks which require the model to infer the underlying mapping. Code is available at https://github.com/yuvenduan/PlasticRNNs.

翻译：摘要：从持续的经验中快速学习，并借助灵活的记忆系统记住过往事件，是生物智能的两项核心能力。尽管其背后的神经机制尚未完全阐明，但多种证据支持突触可塑性在记忆形成与快速学习中发挥关键作用。受这些结果启发，我们为循环神经网络（RNNs）配备可塑性规则，使其能够根据持续经验调整自身参数。除了传统的局部Hebbian可塑性外，我们还提出了一种全局的、基于梯度的可塑性规则，使模型能够朝着自我确定的目标进化。我们的模型在序列记忆与联想记忆任务中展现出良好效果，证明了其鲁棒地形成和保留记忆的能力。同时，这些模型能够应对诸多具有挑战性的小样本学习问题。在统一框架下比较不同可塑性规则表明：Hebbian可塑性适用于多种记忆与联想学习任务，但在要求模型推断底层映射的小样本回归任务中，其表现逊于基于梯度的可塑性。代码见https://github.com/yuvenduan/PlasticRNNs。