Bayesian Metaplasticity from Synaptic Uncertainty
CoRR(2023)
摘要
Catastrophic forgetting remains a challenge for neural networks, especially
in lifelong learning scenarios. In this study, we introduce MEtaplasticity from
Synaptic Uncertainty (MESU), inspired by metaplasticity and Bayesian inference
principles. MESU harnesses synaptic uncertainty to retain information over
time, with its update rule closely approximating the diagonal Newton's method
for synaptic updates. Through continual learning experiments on permuted MNIST
tasks, we demonstrate MESU's remarkable capability to maintain learning
performance across 100 tasks without the need of explicit task boundaries.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要