Mistake gating leads to energy and memory efficient continual learning

arXiv:2604.14336v2 Announce Type: replace Abstract: 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.

Related

• BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding
• When to Stop Reusing: Dynamic Gradient Gating for Sample-Efficient RLVR
• Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates
• ARROW: Augmented Replay for RObust World models

Source: arXiv cs.AI | 2026-07-15