Rochester Institute of Technology, Rochester, NY 14623, U.S.A.
University of California at San Diego, La Jolla, CA 92093, U.S.A.
Neural Comput. 2021 Oct 12;33(11):2908-2950. doi: 10.1162/neco_a_01433.
Replay is the reactivation of one or more neural patterns that are similar to the activation patterns experienced during past waking experiences. Replay was first observed in biological neural networks during sleep, and it is now thought to play a critical role in memory formation, retrieval, and consolidation. Replay-like mechanisms have been incorporated in deep artificial neural networks that learn over time to avoid catastrophic forgetting of previous knowledge. Replay algorithms have been successfully used in a wide range of deep learning methods within supervised, unsupervised, and reinforcement learning paradigms. In this letter, we provide the first comprehensive comparison between replay in the mammalian brain and replay in artificial neural networks. We identify multiple aspects of biological replay that are missing in deep learning systems and hypothesize how they could be used to improve artificial neural networks.
重放是一个或多个神经模式的重新激活，这些模式类似于在过去的清醒经历中经历的激活模式。重放最初在睡眠期间的生物神经网络中被观察到，现在被认为在记忆形成、检索和巩固中起着关键作用。类似重放的机制已经被整合到深度人工神经网络中，这些网络随着时间的推移学习，以避免对以前知识的灾难性遗忘。重放算法已成功应用于监督学习、无监督学习和强化学习范例中的各种深度学习方法中。在这封信中，我们首次对哺乳动物大脑中的重放和人工神经网络中的重放进行了全面比较。我们确定了深度学习系统中缺失的多个生物重放方面，并假设了如何利用它们来改进人工神经网络。
