Using habituation in machine learning |
| |
Authors: | Marsland Stephen |
| |
Affiliation: | aComputer Science Group, School of Engineering and Advanced Technology, Massey University, Private Bag 11-222, Palmerston North 4442, New Zealand |
| |
Abstract: | Habituation, a decrement in response to a stimulus that is presented repeatedly without ill effect, can be identified in almost all animals. It can also be used in machine learning to provide a variety of different applications, such as novelty detection, recency encoding, and temporal signal pre-processing. This paper examines how habituation can be mathematically modelled, and discusses how well these models fit the revised characteristics of habituation. It then demonstrates how the models can be combined with neural networks in order to realise the various applications. Finally, some simple experimental results are presented that demonstrate the effectiveness of the methods. |
| |
Keywords: | Habituation Machine learning Neural network Novelty detection |
本文献已被 ScienceDirect PubMed 等数据库收录! |
|