经验回放解决持续学习中的可塑性丧失问题
Experience Replay Addresses Loss of Plasticity in Continual Learning
AI总结：
本文提出经验回放结合Transformer可解决持续学习中深度网络的可塑性丧失问题，并在回归、分类和策略评估任务中验证了该假设。
摘要：
可塑性丧失是使用深度神经网络进行持续学习时面临的主要挑战之一，在这种情况下，通过反向传播训练的神经网络会逐渐失去适应新任务的能力，其表现明显差于刚初始化时的网络。本文的主要贡献是提出一个新假设：经验回放能够解决持续学习中的可塑性丧失问题。这里，经验回放是一种记忆形式。我们为该假设提供了支持性证据。具体而言，我们在多个不同任务（包括回归、分类和策略评估）中证明，只需简单地添加经验回放，并使用Transformer处理经验回放中的数据，可塑性丧失现象就会消失。值得注意的是，我们没有改变深度学习的任何标准组件。例如，我们没有改变反向传播，没有修改激活函数，也没有使用任何正则化。我们推测，经验回放和Transformer能够解决可塑性丧失问题，是因为上下文学习现象。
英文摘要：
Loss of plasticity is one of the main challenges in continual learning with deep neural networks, where neural networks trained via backpropagation gradually lose their ability to adapt to new tasks and perform significantly worse than their freshly initialized counterparts. The main contribution of this paper is to propose a new hypothesis that experience replay addresses the loss of plasticity in continual learning. Here, experience replay is a form of memory. We provide supporting evidence for this hypothesis. In particular, we demonstrate in multiple different tasks, including regression, classification, and policy evaluation, that by simply adding an experience replay and processing the data in the experience replay with Transformers, the loss of plasticity disappears. Notably, we do not alter any standard components of deep learning. For example, we do not change backpropagation. We do not modify the activation functions. And we do not use any regularization. We conjecture that experience replay and Transformers can address the loss of plasticity because of the in-context learning phenomenon.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
