Cognitive Discriminative Mappings for Rapid Learning
This addresses the challenge of enabling machines to learn quickly from limited data, which is incremental as it builds on existing cognitive and machine learning approaches.
The paper tackles the problem of rapid learning from few examples by proposing cognitive discriminative mappings (CDM), a method that leverages long-term memory to improve learning from sensory input, and shows it is effective for supervised classification with few training instances.
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.