# Generative Continual Concept Learning

## TL;DR

This paper introduces a novel continual learning model inspired by cognitive theories, capable of efficiently expanding learned concepts to new domains with minimal data while mitigating catastrophic forgetting.

## Contribution

It proposes a computational framework that couples new concepts with past ones in an embedding space, enabling effective continual learning and generalization.

## Key findings

- Model effectively expands concepts to new domains with few samples.
- Generates pseudo-data to replay past experiences and prevent forgetting.
- Achieves continual learning without extensive retraining.

## Abstract

After learning a concept, humans are also able to continually generalize their learned concepts to new domains by observing only a few labeled instances without any interference with the past learned knowledge. In contrast, learning concepts efficiently in a continual learning setting remains an open challenge for current Artificial Intelligence algorithms as persistent model retraining is necessary. Inspired by the Parallel Distributed Processing learning and the Complementary Learning Systems theories, we develop a computational model that is able to expand its previously learned concepts efficiently to new domains using a few labeled samples. We couple the new form of a concept to its past learned forms in an embedding space for effective continual learning. Doing so, a generative distribution is learned such that it is shared across the tasks in the embedding space and models the abstract concepts. This procedure enables the model to generate pseudo-data points to replay the past experience to tackle catastrophic forgetting.