Incremental Concept Formation over Visual Images Without Catastrophic Forgetting
This addresses the problem of catastrophic forgetting for researchers and practitioners in machine learning, offering an incremental alternative to neural networks.
The paper tackles catastrophic forgetting in deep neural networks for visual tasks by introducing Cobweb4V, a method that incrementally learns concepts with less data and maintains stable performance without forgetting.
Deep neural networks have excelled in machine learning, particularly in vision tasks, however, they often suffer from catastrophic forgetting when learning new tasks sequentially. In this work, we introduce Cobweb4V, an alternative to traditional neural network approaches. Cobweb4V is a novel visual classification method that 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 Cobweb4Vs proficiency in learning visual concepts, requiring less data to achieve effective learning outcomes compared to traditional methods, maintaining stable performance over time, and achieving commendable asymptotic behavior, without catastrophic forgetting effects. These characteristics align with learning strategies in human cognition, positioning Cobweb4V as a promising alternative to neural network approaches.