A Study of Biologically Plausible Neural Network: The Role and Interactions of Brain-Inspired Mechanisms in Continual Learning
Not on the map. Why?
Abstract (arXiv)
Humans excel at continually acquiring, consolidating, and retaining information from an ever-changing environment, whereas artificial neural networks (ANNs) exhibit catastrophic forgetting. There are considerable differences in the complexity of synapses, the processing of information, and the learning mechanisms in biological neural networks and their artificial counterparts, which may explain the mismatch in performance. We consider a biologically plausible framework that constitutes separate populations of exclusively excitatory and inhibitory neurons that adhere to Dale's principle, and the excitatory pyramidal neurons are augmented with dendritic-like structures for context-dependent processing of stimuli. We then conduct a comprehensive study on the role and interactions of different mechanisms inspired by the brain, including sparse non-overlapping representations, Hebbian learning, synaptic consolidation, and replay of past activations that accompanied the learning event. Our study suggests that the employing of multiple complementary mechanisms in a biologically plausible architecture, similar to the brain, may be effective in enabling continual learning in ANNs.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 17 of its 56 references that are in the map. First posted on arXiv 13 Apr 2023.
Builds on
17 of 56 references.
References · 17
- 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
- 2016Learning without Forgettingcited by 2,496
- 2017Gradient Episodic Memory for Continual Learningcited by 1,898
- 2018Efficient Lifelong Learning with A-GEMcited by 1,058
- 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 742
- 2018Continual Learning of Context-dependent Processing in Neural Networkscited by 179
- 2018Towards Robust Evaluations of Continual Learningcited by 148
- 2022Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning Systemcited by 112
- 2021Replay in Deep Learning: Current Approaches and Missing Biological Elementscited by 72
- 2019How Can We Be So Dense? The Benefits of Using Highly Sparse Representationscited by 45
- 2018Selfless Sequential Learningcited by 44
- 2018Biologically-plausible learning algorithms can scale to large datasetscited by 37
5 more
- 2021Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environmentscited by 25
- 2022Sparsity and Heterogeneous Dropout for Continual Learning in the Null Space of Neural Activationscited by 19
- 2021Two Sparsities Are Better Than One: Unlocking the Performance Benefits of Sparse-Sparse Networkscited by 15
- 2022Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signalscited by 12
- 2018Training dynamically balanced excitatory-inhibitory networkscited by 3
Built on by
Citing papers per year: 2024: 1.
1 paper.