历史学习研究综述：具有学习历史的学习模式
A Survey of Historical Learning: Learning Models with Learning History
摘要：
新知识来源于旧知识。在训练历史中沉积的各种类型的元素是改进深度模型学习的大量财富。在本次调查中，我们全面回顾和总结了“历史学习：具有学习历史的学习模型”这一主题，即在优化过程中借助学习历史来学习更好的神经模型，从三个详细方面：历史类型（什么），功能部分（哪里）和存储形式（如何）。据我们所知，这是第一次系统地研究在训练深度神经网络时利用各种历史统计数据的方法。与相关主题的讨论，如循环/记忆网络，集成学习，和强化学习演示。我们还揭示了这个主题未来的挑战，并鼓励社区在设计算法时注意考虑历史学习原则。与历史学习相关的论文列表可在\url{https://github.com/Martinser/Awesome-Historical-Learning.}上获得
英文摘要：
New knowledge originates from the old. The various types of elements, deposited in the training history, are a large amount of wealth for improving learning deep models. In this survey, we comprehensively review and summarize the topic--``Historical Learning: Learning Models with Learning History'', which learns better neural models with the help of their learning history during its optimization, from three detailed aspects: Historical Type (what), Functional Part (where) and Storage Form (how). To our best knowledge, it is the first survey that systematically studies the methodologies which make use of various historical statistics when training deep neural networks. The discussions with related topics like recurrent/memory networks, ensemble learning, and reinforcement learning are demonstrated. We also expose future challenges of this topic and encourage the community to pay attention to the think of historical learning principles when designing algorithms. The paper list related to historical learning is available at \url{https://github.com/Martinser/Awesome-Historical-Learning.}
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。
