Lazy learning: a biologically-inspired plasticity rule for fast and energy efficient synaptic plasticity
(2023)
Working Paper
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 concentrate their learning effort on errors. Inspired by human learnin... Read More about Lazy learning: a biologically-inspired plasticity rule for fast and energy efficient synaptic plasticity.