3 papers
cs.AI2026
Mistake gating leads to energy and memory efficient continual learning
Aaron Pache, Mark CW van Rossum
Synaptic plasticity is metabolically expensive, yet animals continuously update their internal models without exhausting energy reserves. However, when artificial neural networks a…
cs.NE2023
Competitive plasticity to reduce the energetic costs of learning
Mark CW van Rossum
The brain is not only constrained by energy needed to fuel computation, but it is also constrained by energy needed to form memories. Experiments have shown that learning simple co…
cs.NE2023
Lazy learning: a biologically-inspired plasticity rule for fast and energy efficient synaptic plasticity
Aaron Pache, Mark CW van Rossum
When training neural networks for classification tasks with backpropagation, parameters are updated on every trial, even if the sample is classified correctly. In contrast, humans…