用发展性压缩对抗灾难性遗忘
Combating catastrophic forgetting with developmental compression
摘要：
一般来说，智能代理在几种设置中表现出成功的行为。在机器中实现这种智能的方法中，普遍存在灾难性遗忘：顺序学习破坏了在顺序中较早获得的知识，或者任务对抗性地竞争系统资源。用于避免灾难性遗忘的方法已经寻求识别和保留在学习解决一个问题时解决另一个问题所必需的系统特征，或者寻求加强模块化，使得最小重叠的子功能包含任务特定的知识。虽然这两种方法都很成功，但它们的扩展性都很差，因为随着训练实例数量的增加，它们需要更大的架构，导致系统的不同部分专门用于不同的数据子集。在这里，我们提出了一种解决灾难性遗忘的方法，称为发展压缩。它利用发育突变的轻微影响来减少对先前进化能力的不利变化，并将专门的神经网络“压缩”成一个通用的网络。在没有领域知识的情况下，发展压缩产生的系统，避免了明显的专业化，减轻了需要工程师定制的系统，每一个任务排列，并建议更好的可扩展性比现有的方法。我们在机器人控制问题上验证了这种方法，并希望将来将这种方法扩展到其他机器学习领域。
英文摘要：
Generally intelligent agents exhibit successful behavior across problems in several settings. Endemic in approaches to realize such intelligence in machines is catastrophic forgetting: sequential learning corrupts knowledge obtained earlier in the sequence, or tasks antagonistically compete for system resources. Methods for obviating catastrophic forgetting have sought to identify and preserve features of the system necessary to solve one problem when learning to solve another, or to enforce modularity such that minimally overlapping sub-functions contain task specific knowledge. While successful, both approaches scale poorly because they require larger architectures as the number of training instances grows, causing different parts of the system to specialize for separate subsets of the data. Here we present a method for addressing catastrophic forgetting called developmental compression. It exploits the mild impacts of developmental mutations to lessen adverse changes to previously-evolved capabilities and `compresses' specialized neural networks into a generalized one. In the absence of domain knowledge, developmental compression produces systems that avoid overt specialization, alleviating the need to engineer a bespoke system for every task permutation and suggesting better scalability than existing approaches. We validate this method on a robot control problem and hope to extend this approach to other machine learning domains in the future.
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。
