Bridging Neuroscience and AI: Environmental Enrichment as a Model for Forward Knowledge Transfer
Not on the map. Why?
Abstract (arXiv)
Continual learning (CL) refers to an agent's capability to learn from a continuous stream of data and transfer knowledge without forgetting old information. One crucial aspect of CL is forward transfer, i.e., improved and faster learning on a new task by leveraging information from prior knowledge. While this ability comes naturally to biological brains, it poses a significant challenge for artificial intelligence (AI). Here, we suggest that environmental enrichment (EE) can be used as a biological model for studying forward transfer, inspiring human-like AI development. EE refers to animal studies that enhance cognitive, social, motor, and sensory stimulation and is a model for what, in humans, is referred to as 'cognitive reserve'. Enriched animals show significant improvement in learning speed and performance on new tasks, typically exhibiting forward transfer. We explore anatomical, molecular, and neuronal changes post-EE and discuss how artificial neural networks (ANNs) can be used to predict neural computation changes after enriched experiences. Finally, we provide a synergistic way of combining neuroscience and AI research that paves the path toward developing AI capable of rapid and efficient new task learning.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 130 references that are in the map. First posted on arXiv 12 May 2024.
Builds on
22 of 130 references.
References · 22
- 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
- 2019Online Continual Learning with Maximally Interfered Retrievalcited by 376
- 2018Markerless tracking of user-defined features with deep learningcited by 203
- 2018A mathematical theory of semantic development in deep neural networkscited by 182
- 2020Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semanticscited by 158
- 2018Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilizationcited by 104
- 2021Achieving Forgetting Prevention and Knowledge Transfer in Continual Learningcited by 91
- 2016Towards an integration of deep learning and neurosciencecited by 77
- 2021Replay in Deep Learning: Current Approaches and Missing Biological Elementscited by 71
- 2021Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Datacited by 67
- 2021Continual Learning via Local Module Compositioncited by 61
- 2019Ablation Studies in Artificial Neural Networkscited by 58
10 more
- 2021Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Typescited by 54
- 2022Information-theoretic Online Memory Selection for Continual Learningcited by 42
- 2020Meta-learning in natural and artificial intelligencecited by 39
- 2020Unsupervised deep learning identifies semantic disentanglement in single inferotemporal neuronscited by 33
- 2019Continual Learning in Neural Networkscited by 23
- 2022Compositional generalization through abstract representations in human and artificial neural networkscited by 21
- 2022A Theory for Knowledge Transfer in Continual Learningcited by 16
- 2019Sequential mastery of multiple visual tasks: Networks naturally learn to learn and forget to forgetcited by 13
- 2022Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signalscited by 12
- 2020Uncertainty-based Modulation for Lifelong Learningcited by 5
Built on by
Citing papers per year: 2025: 1.
1 paper.