Humans learn all their life long. They accumulate knowledge from a sequence of learning experiences and remember the essential concepts without forgetting what they have learned previously. Artificial neural networks struggle to learn similarly. They often rely on data rigorously preprocessed to learn solutions to specific problems such as classification or regression. In particular, they forget their past learning experiences if trained on new ones. Therefore, artificial neural networks are often inept to deal with real-life settings such as an autonomous-robot that has to learn on-line to adapt to new situations and overcome new problems without forgetting its past learning-experiences. Continual learning (CL) is a branch of machine learning addressing this type of problem. Continual algorithms are designed to accumulate and improve knowledge in a curriculum of learning-experiences without forgetting. In this thesis, we propose to explore continual algorithms with replay processes. Replay processes gather together rehearsal methods and generative replay methods. Generative Replay consists of regenerating past learning experiences with a generative model to remember them. Rehearsal consists of saving a core-set of samples from past learning experiences to rehearse them later. The replay processes make possible a compromise between optimizing the current learning objective and the past ones enabling learning without forgetting in sequences of tasks settings. We show that they are very promising methods for continual learning. Notably, they enable the re-evaluation of past data with new knowledge and the confrontation of data from different learning-experiences. We demonstrate their ability to learn continually through unsupervised learning, supervised learning and reinforcement learning tasks.
翻译:人类从整个人生中学习。 他们从一系列学习经验中积累知识, 并记住基本概念, 而不会忘记他们以前所学过的东西。 人工神经网络努力学习相似。 他们常常依靠严格预处理的数据来学习分类或回归等具体问题的解决方案。 特别是, 他们忘记了过去学习新课程的经验。 因此, 人工神经网络往往无法处理现实生活环境, 例如自主机器人, 它必须在线学习适应新情况, 克服新问题, 而不忘记过去的学习经验。 持续学习( CL) 是处理这类问题的机器学习的分支。 连续算法的设计是要在学习经验的课程中积累和增加知识, 而不会忘记。 在这个理论中, 我们提议探索持续算法, 用重播程序, 重新演练方法, 并重塑基因模型, 以记住它们。 重现的重现, 不断学习包括从过去学习经验的不精选样中保存一个核心的样本, 不断学习它们, 不断学习它们的能力, 重新演练它们。 我们重新演练过去的工作, 重新演练, 重新演练, 重新演练, 重新演进, 重新演, 重新演, 重新演, 重新演练, 重新演练, 重新演练, 重新演练, 重新演练, 重新演练, 重新演进, 重新演进, 重新演练, 重新演进, 重新演练, 重新演练, 学习, 重新演, 重新演练, 重新演进, 重新演练, 重新演进。