Continual Learning of Multiple Cognitive Functions with Brain-inspired Temporal Development Mechanism
Not on the map. Why?
Abstract (arXiv)
Cognitive functions in current artificial intelligence networks are tied to the exponential increase in network scale, whereas the human brain can continuously learn hundreds of cognitive functions with remarkably low energy consumption. This advantage is in part due to the brain cross-regional temporal development mechanisms, where the progressive formation, reorganization, and pruning of connections from basic to advanced regions, facilitate knowledge transfer and prevent network redundancy. Inspired by these, we propose the Continual Learning of Multiple Cognitive Functions with Brain-inspired Temporal Development Mechanism(TD-MCL), enabling cognitive enhancement from simple to complex in Perception-Motor-Interaction(PMI) multiple cognitive task scenarios. The TD-MCL model proposes the sequential evolution of long-range connections between different cognitive modules to promote positive knowledge transfer, while using feedback-guided local connection inhibition and pruning to effectively eliminate redundancies in previous tasks, reducing energy consumption while preserving acquired knowledge. Experiments show that the proposed method can achieve continual learning capabilities while reducing network scale, without introducing regularization, replay, or freezing strategies, and achieving superior accuracy on new tasks compared to direct learning. The proposed method shows that the brain's developmental mechanisms offer a valuable reference for exploring biologically plausible, low-energy enhancements of general cognitive abilities.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 34 of its 85 references that are in the map. First posted on arXiv 8 Apr 2025.
Builds on
34 of 85 references.
References · 34
- 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
- 2016Learning without Forgettingcited by 2,465
- 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
- 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,168
- 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,094
- 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 895
- 2019Large Scale Incremental Learningcited by 727
- 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 672
- 2020Deep Domain-Adversarial Image Generation for Domain Generalisationcited by 231
- 2020Supermasks in Superpositioncited by 223
- 2020Mnemonics Training: Multi-Class Incremental Learning without Forgettingcited by 220
- 2019Compacting, Picking and Growing for Unforgetting Continual Learningcited by 207
22 more
- 2018Continual Learning of Context-dependent Processing in Neural Networkscited by 178
- 2019Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networkscited by 118
- 2015Data-free parameter pruning for Deep Neural Networkscited by 112
- 2023Dense Network Expansion for Class Incremental Learningcited by 45
- 2023Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge Distillationcited by 41
- 2023Continual Learning with Scaled Gradient Projectioncited by 33
- 2021A Fully Spiking Hybrid Neural Network for Energy-Efficient Object Detectioncited by 31
- 2023ESL-SNNs: An Evolutionary Structure Learning Strategy for Spiking Neural Networkscited by 22
- 2021Saliency Guided Experience Packing for Replay in Continual Learningcited by 14
- 2021Relational Experience Replay: Continual Learning by Adaptively Tuning Task-wise Relationshipcited by 11
- 2024Enhancing Adaptive History Reserving by Spiking Convolutional Block Attention Module in Recurrent Neural Networkscited by 10
- 2022Adaptive Sparse Structure Development with Pruning and Regeneration for Spiking Neural Networkscited by 9
- 2023Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantizationcited by 9
- 2024Towards Efficient Deep Spiking Neural Networks Construction with Spiking Activity based Pruningcited by 9
- 2024EVCL: Elastic Variational Continual Learning with Weight Consolidationcited by 9
- 2023Continual Learning with Dynamic Sparse Training: Exploring Algorithms for Effective Model Updatescited by 8
- 2022TAME: Task Agnostic Continual Learning using Multiple Expertscited by 7
- 2023Adaptive Reorganization of Neural Pathways for Continual Learning with Spiking Neural Networkscited by 7
- 2022Continual Learning with Dependency Preserving Hypernetworkscited by 6
- 2022Developmental Plasticity-inspired Adaptive Pruning for Deep Spiking and Artificial Neural Networkscited by 6
- 2025Do Your Best and Get Enough Rest for Continual Learningcited by 5
- 2024Similarity-based context aware continual learning for spiking neural networkscited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.