Convolutional Cobweb: A Model of Incremental Learning from 2D Images

TL;DR

This paper introduces Convolutional Cobweb, a novel incremental learning model combining convolutional image processing with psychological concept formation, evaluated on digit recognition tasks to bridge computer vision and cognitive science.

Contribution

It presents a new incremental learning approach that integrates convolutional processing with concept formation, unifying computer vision techniques with psychological models.

Findings

Outperforms non-convolutional Cobweb in image tasks

Comparable to convolutional neural networks in accuracy

Supports incremental learning from visual data

Abstract

This paper presents a new concept formation approach that supports the ability to incrementally learn and predict labels for visual images. This work integrates the idea of convolutional image processing, from computer vision research, with a concept formation approach that is based on psychological studies of how humans incrementally form and use concepts. We experimentally evaluate this new approach by applying it to an incremental variation of the MNIST digit recognition task. We compare its performance to Cobweb, a concept formation approach that does not support convolutional processing, as well as two convolutional neural networks that vary in the complexity of their convolutional processing. This work represents a first step towards unifying modern computer vision ideas with classical concept formation research.