# Realizing Continual Learning through Modeling a Learning System as a Fiber Bundle

## TL;DR

This paper introduces a fiber bundle-based model for continual learning in neural networks, addressing catastrophic forgetting and mimicking human memory properties, with improved performance and high information capacity.

## Contribution

The paper proposes a novel fiber bundle framework for neural networks that enhances continual learning and models human-like memory properties.

## Key findings

- The fiber bundle model outperforms traditional neural networks in continual learning tasks.
- Making the model time-aware further improves learning performance.
- The forgetting behavior of the model aligns with human memory characteristics.

## Abstract

A human brain is capable of continual learning by nature; however the current mainstream deep neural networks suffer from a phenomenon named catastrophic forgetting (i.e., learning a new set of patterns suddenly and completely would result in fully forgetting what has already been learned). In this paper we propose a generic learning model, which regards a learning system as a fiber bundle. By comparing the learning performance of our model with conventional ones whose neural networks are multilayer perceptrons through a variety of machine-learning experiments, we found our proposed model not only enjoys a distinguished capability of continual learning but also bears a high information capacity. In addition, we found in some learning scenarios the learning performance can be further enhanced by making the learning time-aware to mimic the episodic memory in human brain. Last but not least, we found that the properties of forgetting in our model correspond well to those of human memory. This work may shed light on how a human brain learns.