只在出错时更新参数，让神经网络更省电省内存。
Mistake gating leads to energy and memory efficient continual learning
- 出错才更新，减少50%~80%的参数调整次数。
- 在增量学习和在线学习中显著降低存储需求。
- 无需调参、代码简单，适合边缘设备持续学习。
突触可塑性代谢成本高，但动物能持续更新内部模型而不耗尽能量。而传统人工神经网络在每条样本上都会更新参数，即使分类正确。受人类负向偏见和错误相关负电位启发，我们提出“记忆错误门控学习”——一种生物合理的学习规则，仅在当前或过去出现分类错误时才进行突触更新。该方法将网络所需更新次数减少50%~80%。该机制特别适用于两种场景：1）增量学习中，在已有知识基础上获取新知识；2）在线学习中需存储数据以供后续回放时，大幅降低存储缓冲区需求。算法实现仅需几行代码，不增加超参数，计算开销极低。基于错误的学习是一种节能且生物合理的改进，非常适合持续学习任务。
原文摘要 · Abstract (English)
Synaptic plasticity is metabolically expensive, yet animals continuously update their internal models without exhausting energy reserves. However, when artificial neural networks are trained, the network parameters are typically updated on every sample that is presented, even if the sample was classified correctly. Inspired by the human negativity bias and error-related negativity, we propose 'memorized mistake-gated learning' -- a biologically plausible plasticity rule where synaptic updates are strictly gated by current and past classification errors. This reduces the number of updates the network needs to make by $50\%\sim80\%$. Mistake gating is particularly well suited in two cases: 1) For incremental learning where new knowledge is acquired on a background of pre-existing knowledge, 2) For online learning scenarios when data needs to be stored for later replay, as mistake-gating reduces storage buffer requirements. The algorithm can be implemented in a few lines of code, adds no hyper-parameters, and comes at negligible computational overhead. Learning on mistakes is an energy efficient and biologically relevant modification to commonly used learning rules that is well suited for continual learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。