FearNet: Brain-Inspired Model for Incremental Learning

TL;DR

FearNet is a brain-inspired generative model for incremental learning that avoids storing previous data, consolidates memories inspired by sleep mechanisms, and achieves state-of-the-art results on image and audio benchmarks.

Contribution

It introduces a novel dual-memory system inspired by brain structures and sleep processes, enabling scalable incremental learning without storing past examples.

Findings

Outperforms existing methods on CIFAR-100, CUB-200, and AudioSet.

Memory consolidation inspired by sleep improves learning stability.

Memory system selector enhances recall accuracy.

Abstract

Incremental class learning involves sequentially learning classes in bursts of examples from the same class. This violates the assumptions that underlie methods for training standard deep neural networks, and will cause them to suffer from catastrophic forgetting. Arguably, the best method for incremental class learning is iCaRL, but it requires storing training examples for each class, making it challenging to scale. Here, we propose FearNet for incremental class learning. FearNet is a generative model that does not store previous examples, making it memory efficient. FearNet uses a brain-inspired dual-memory system in which new memories are consolidated from a network for recent memories inspired by the mammalian hippocampal complex to a network for long-term storage inspired by medial prefrontal cortex. Memory consolidation is inspired by mechanisms that occur during sleep. FearNet also uses a module inspired by the basolateral amygdala for determining which memory system to use for recall. FearNet achieves state-of-the-art performance at incremental class learning on image (CIFAR-100, CUB-200) and audio classification (AudioSet) benchmarks.