Article

Memory Consolidation with Orthogonal Gradients for avoiding Catastrophic Forgetting

2022-02-28

Abstract excerpt

The memory consolidation process enables the accumulation of recent and remote memories in the long-term memory store. In general, the deep network models of memory suffer from forgetting old information while learning new information, called catastrophic forgetting/interference. The human brain overcomes this problem quite effectively, a problem that continues to challenge current deep neural network models. We p...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 9f7576c0-331d-5402-8afd-281ca9a5a7fa
DOI: 10.1101/2022.02.25.481890

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Memory Consolidation with Orthogonal Gradients for avoiding Catastrophic ForgettingDOI 10.1101/2022.02.25.481890Read

Memory Consolidation with Orthogonal Gradients for avoiding Catastrophic ForgettingSemantic proximity Read

Overcoming Catastrophic Interference: Neuroscience-inspired Models for Continuous Learning in Neural NetworksSemantic proximity Read

A neural network account of memory replay and knowledge consolidationSemantic proximity Read

Backpropagation-Free Continual Learning: A Unified Energy-Based Framework, Reproducible Benchmark, and Open ChallengesSemantic proximity Read

Learning sculpts orthogonal task manifolds for continual skill learning in recurrent networksSemantic proximity Read

AMG: a memory generation model based on Hebbian plasticity and inferential associationSemantic proximity Read

Computational Decomposition of New Memory Failure in Alzheimers Disease Through a Hippocampal Cortical Consolidation Bottleneck ModelSemantic proximity Read

Flexible working memory through selective gating and attentional taggingSemantic proximity Read

Sleep ripples drive single-neuron reactivation for human memory consolidationSemantic proximity Read

Scaffolded representation learning in deep networksSemantic proximity Read

One-shot memory in hippocampal CA3 networks.Semantic proximity Read

A bio-inspired hybrid lifelong learning based on self-selective memristorsSemantic proximity Read