Cognitive Discriminative Mappings for Rapid Learning

TL;DR

This paper introduces Cognitive Discriminative Mappings (CDM), a novel computational model inspired by human rapid learning, which effectively classifies data with minimal training samples by leveraging long-term memory information.

Contribution

The paper proposes the CDM technique that clusters and maps sensory data to discriminative class medians, enabling rapid learning with few examples, inspired by cognitive processes.

Findings

Effective in supervised classification with limited data

Clusters long-term memory data into distinct classes

Maps sensory inputs close to class medians

Abstract

Humans can learn concepts or recognize items from just a handful of examples, while machines require many more samples to perform the same task. In this paper, we build a computational model to investigate the possibility of this kind of rapid learning. The proposed method aims to improve the learning task of input from sensory memory by leveraging the information retrieved from long-term memory. We present a simple and intuitive technique called cognitive discriminative mappings (CDM) to explore the cognitive problem. First, CDM separates and clusters the data instances retrieved from long-term memory into distinct classes with a discrimination method in working memory when a sensory input triggers the algorithm. CDM then maps each sensory data instance to be as close as possible to the median point of the data group with the same class. The experimental results demonstrate that the CDM approach is effective for learning the discriminative features of supervised classifications with few training sensory input instances.