论文标题
快速学习，学习缓慢：一种基于互补学习系统的一般持续学习方法
Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System
论文作者
论文摘要
人类在不断变化的环境中不断学习，而对于表现出灾难性遗忘的深度神经网络仍然是一个挑战。补充学习系统（CLS）理论表明，基于实例的学习与大脑中结构缓慢的学习之间的相互作用对于积累和保留知识至关重要。在这里，我们提出了CLS-ER，这是一种新型的双重记忆体验重播（ER）方法，该方法保持短期和长期的语义记忆与情节记忆相互作用。我们的方法采用了一种有效的重播机制，在该机制中获得了新知识，同时将决策界限与语义记忆保持一致。 CLS-ER不利用任务边界或对数据的分布做出任何假设，这使其具有多功能和适合“一般持续学习”。我们的方法在标准基准和更现实的一般持续学习环境方面实现了最先进的表现。
Humans excel at continually learning from an ever-changing environment whereas it remains a challenge for deep neural networks which exhibit catastrophic forgetting. The complementary learning system (CLS) theory suggests that the interplay between rapid instance-based learning and slow structured learning in the brain is crucial for accumulating and retaining knowledge. Here, we propose CLS-ER, a novel dual memory experience replay (ER) method which maintains short-term and long-term semantic memories that interact with the episodic memory. Our method employs an effective replay mechanism whereby new knowledge is acquired while aligning the decision boundaries with the semantic memories. CLS-ER does not utilize the task boundaries or make any assumption about the distribution of the data which makes it versatile and suited for "general continual learning". Our approach achieves state-of-the-art performance on standard benchmarks as well as more realistic general continual learning settings.
