Robust incremental learning of visual concepts without catastrophic forgetting

• We introduce Cobweb/4V, a new extension of the concept formation system, Cobweb, that supports vision tasks. • We show that Cobweb/4V can learn quickly and achieve strong performance, demonstrating the potential of a modular, instance-based approach for data-efficient learning. • We demonstrate that Cobweb/4V is resistant to catastrophic forgetting and exhibits only minimal performance decay due to interference, emphasizing its stability and robustness during continual learning. Continual learning poses a significant challenge in machine learning, as models often struggle to retain previously learned knowledge when exposed to new data, leading to catastrophic forgetting. In this work, we introduce Cobweb/4V , a novel visual classification method. This approach builds on Cobweb, a human-like learning system that is inspired by the way humans incrementally learn new concepts over time. In this research, we conduct a comprehensive evaluation showcasing Cobweb/4V’s proficiency in learning visual concepts, requiring less data to achieve effective learning outcomes compared to neural network approaches, maintaining stable performance over time, achieving competitive asymptotic behavior, and avoiding catastrophic forgetting. These characteristics align with human learning capabilities, positioning Cobweb/4V as a promising approach for sequential learning and motivating future exploration into its potential to guide the development of neural networks and other machine learning approaches that handle continual learning.