English

A Biologically Plausible Audio-Visual Integration Model for Continual Learning

Neural and Evolutionary Computing 2021-07-21 v2 Artificial Intelligence Neurons and Cognition

Abstract

The problem of catastrophic forgetting has a history of more than 30 years and has not been completely solved yet. Since the human brain has natural ability to perform continual lifelong learning, learning from the brain may provide solutions to this problem. In this paper, we propose a novel biologically plausible audio-visual integration model (AVIM) based on the assumption that the integration of audio and visual perceptual information in the medial temporal lobe during learning is crucial to form concepts and make continual learning possible. Specifically, we use multi-compartment Hodgkin-Huxley neurons to build the model and adopt the calcium-based synaptic tagging and capture as the model's learning rule. Furthermore, we define a new continual learning paradigm to simulate the possible continual learning process in the human brain. We then test our model under this new paradigm. Our experimental results show that the proposed AVIM can achieve state-of-the-art continual learning performance compared with other advanced methods such as OWM, iCaRL and GEM. Moreover, it can generate stable representations of objects during learning. These results support our assumption that concept formation is essential for continuous lifelong learning and suggest the proposed AVIM is a possible concept formation mechanism.

Keywords

Cite

@article{arxiv.2007.08855,
  title  = {A Biologically Plausible Audio-Visual Integration Model for Continual Learning},
  author = {Wenjie Chen and Fengtong Du and Ye Wang and Lihong Cao},
  journal= {arXiv preprint arXiv:2007.08855},
  year   = {2021}
}

Comments

Accepted by 2021 International Joint Conference on Neural Networks

R2 v1 2026-06-23T17:11:30.104Z