Saved in:
Bibliographic Details
Main Authors: Ran, Xuming, Yao, Juntao, Wang, Yusong, Xu, Mingkun, Liu, Dianbo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.05899
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910640988225536
author Ran, Xuming
Yao, Juntao
Wang, Yusong
Xu, Mingkun
Liu, Dianbo
author_facet Ran, Xuming
Yao, Juntao
Wang, Yusong
Xu, Mingkun
Liu, Dianbo
contents Pre-trained models have demonstrated impressive generalization capabilities, yet they remain vulnerable to catastrophic forgetting when incrementally trained on new tasks. Existing architecture-based strategies encounter two primary challenges: 1) Integrating a pre-trained network with a trainable sub-network complicates the delicate balance between learning plasticity and memory stability across evolving tasks during learning. 2) The absence of robust interconnections between pre-trained networks and various sub-networks limits the effective retrieval of pertinent information during inference. In this study, we introduce the Artsy, inspired by the activation mechanisms of silent synapses via spike-timing-dependent plasticity observed in mature brains, to enhance the continual learning capabilities of pre-trained models. The Artsy integrates two key components: During training, the Artsy mimics mature brain dynamics by maintaining memory stability for previously learned knowledge within the pre-trained network while simultaneously promoting learning plasticity in task-specific sub-networks. During inference, artificial silent and functional synapses are utilized to establish precise connections between the pre-synaptic neurons in the pre-trained network and the post-synaptic neurons in the sub-networks, facilitated through synaptic consolidation, thereby enabling effective extraction of relevant information from test samples. Comprehensive experimental evaluations reveal that our model significantly outperforms conventional methods on class-incremental learning tasks, while also providing enhanced biological interpretability for architecture-based approaches. Moreover, we propose that the Artsy offers a promising avenue for simulating biological synaptic mechanisms, potentially advancing our understanding of neural plasticity in both artificial and biological systems.
format Preprint
id arxiv_https___arxiv_org_abs_2410_05899
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Brain-inspired continual pre-trained learner via silent synaptic consolidation
Ran, Xuming
Yao, Juntao
Wang, Yusong
Xu, Mingkun
Liu, Dianbo
Machine Learning
Pre-trained models have demonstrated impressive generalization capabilities, yet they remain vulnerable to catastrophic forgetting when incrementally trained on new tasks. Existing architecture-based strategies encounter two primary challenges: 1) Integrating a pre-trained network with a trainable sub-network complicates the delicate balance between learning plasticity and memory stability across evolving tasks during learning. 2) The absence of robust interconnections between pre-trained networks and various sub-networks limits the effective retrieval of pertinent information during inference. In this study, we introduce the Artsy, inspired by the activation mechanisms of silent synapses via spike-timing-dependent plasticity observed in mature brains, to enhance the continual learning capabilities of pre-trained models. The Artsy integrates two key components: During training, the Artsy mimics mature brain dynamics by maintaining memory stability for previously learned knowledge within the pre-trained network while simultaneously promoting learning plasticity in task-specific sub-networks. During inference, artificial silent and functional synapses are utilized to establish precise connections between the pre-synaptic neurons in the pre-trained network and the post-synaptic neurons in the sub-networks, facilitated through synaptic consolidation, thereby enabling effective extraction of relevant information from test samples. Comprehensive experimental evaluations reveal that our model significantly outperforms conventional methods on class-incremental learning tasks, while also providing enhanced biological interpretability for architecture-based approaches. Moreover, we propose that the Artsy offers a promising avenue for simulating biological synaptic mechanisms, potentially advancing our understanding of neural plasticity in both artificial and biological systems.
title Brain-inspired continual pre-trained learner via silent synaptic consolidation
topic Machine Learning
url https://arxiv.org/abs/2410.05899