Saved in:
Bibliographic Details
Main Authors: Du, Jin, Zhang, Xinhe, Shen, Hao, Xian, Xun, Wang, Ganghua, Zhang, Jiawei, Yang, Yuhong, Li, Na, Liu, Jia, Ding, Jie
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.13997
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912039485571072
author Du, Jin
Zhang, Xinhe
Shen, Hao
Xian, Xun
Wang, Ganghua
Zhang, Jiawei
Yang, Yuhong
Li, Na
Liu, Jia
Ding, Jie
author_facet Du, Jin
Zhang, Xinhe
Shen, Hao
Xian, Xun
Wang, Ganghua
Zhang, Jiawei
Yang, Yuhong
Li, Na
Liu, Jia
Ding, Jie
contents Lifelong learning in artificial intelligence (AI) aims to mimic the biological brain's ability to continuously learn and retain knowledge, yet it faces challenges such as catastrophic forgetting. Recent neuroscience research suggests that neural activity in biological systems undergoes representational drift, where neural responses evolve over time, even with consistent inputs and tasks. We hypothesize that representational drift can alleviate catastrophic forgetting in AI during new task acquisition. To test this, we introduce DriftNet, a network designed to constantly explore various local minima in the loss landscape while dynamically retrieving relevant tasks. This approach ensures efficient integration of new information and preserves existing knowledge. Experimental studies in image classification and natural language processing demonstrate that DriftNet outperforms existing models in lifelong learning. Importantly, DriftNet is scalable in handling a sequence of tasks such as sentiment analysis and question answering using large language models (LLMs) with billions of parameters on a single Nvidia A100 GPU. DriftNet efficiently updates LLMs using only new data, avoiding the need for full dataset retraining. Tested on GPT-2 and RoBERTa, DriftNet is a robust, cost-effective solution for lifelong learning in LLMs. This study not only advances AI systems to emulate biological learning, but also provides insights into the adaptive mechanisms of biological neural systems, deepening our understanding of lifelong learning in nature.
format Preprint
id arxiv_https___arxiv_org_abs_2409_13997
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Drift to Remember
Du, Jin
Zhang, Xinhe
Shen, Hao
Xian, Xun
Wang, Ganghua
Zhang, Jiawei
Yang, Yuhong
Li, Na
Liu, Jia
Ding, Jie
Artificial Intelligence
Neurons and Cognition
Lifelong learning in artificial intelligence (AI) aims to mimic the biological brain's ability to continuously learn and retain knowledge, yet it faces challenges such as catastrophic forgetting. Recent neuroscience research suggests that neural activity in biological systems undergoes representational drift, where neural responses evolve over time, even with consistent inputs and tasks. We hypothesize that representational drift can alleviate catastrophic forgetting in AI during new task acquisition. To test this, we introduce DriftNet, a network designed to constantly explore various local minima in the loss landscape while dynamically retrieving relevant tasks. This approach ensures efficient integration of new information and preserves existing knowledge. Experimental studies in image classification and natural language processing demonstrate that DriftNet outperforms existing models in lifelong learning. Importantly, DriftNet is scalable in handling a sequence of tasks such as sentiment analysis and question answering using large language models (LLMs) with billions of parameters on a single Nvidia A100 GPU. DriftNet efficiently updates LLMs using only new data, avoiding the need for full dataset retraining. Tested on GPT-2 and RoBERTa, DriftNet is a robust, cost-effective solution for lifelong learning in LLMs. This study not only advances AI systems to emulate biological learning, but also provides insights into the adaptive mechanisms of biological neural systems, deepening our understanding of lifelong learning in nature.
title Drift to Remember
topic Artificial Intelligence
Neurons and Cognition
url https://arxiv.org/abs/2409.13997