Publication Type

Conference Proceeding Article

Publication Date

6-2008

Abstract

Traditional approaches to integrating knowledge into neural network are concerned mainly about supervised learning. This paper presents how a family of self-organizing neural models known as fusion architecture for learning, cognition and navigation (FALCON) can incorporate a priori knowledge and perform knowledge refinement and expansion through reinforcement learning. Symbolic rules are formulated based on pre-existing know-how and inserted into FALCON as a priori knowledge. The availability of knowledge enables FALCON to start performing earlier in the initial learning trials. Through a temporal-difference (TD) learning method, the inserted rules can be refined and expanded according to the evaluative feedback signals received from the environment. Our experimental results based on a minefield navigation task have shown that FALCON is able to learn much faster and attain a higher level of performance earlier when inserted with the appropriate a priori knowledge.

Keywords

self-organizing neural model, reinforcement learning, supervised learning, fusion architecture, cognition, knowledge refinement, symbolic rule, temporal-difference learning method

Discipline

Databases and Information Systems | OS and Networks

Research Areas

Data Science and Engineering

Publication

2008 IEEE International Joint Conference on Neural Networks IJCNN: Hong Kong, June 1-8: Proceedings

First Page

3771

Last Page

3778

ISBN

9781424418206

Identifier

10.1109/IJCNN.2008.4634340

Publisher

IEEE

City or Country

Piscataway, NJ

Additional URL

https://doi.org/10.1109/IJCNN.2008.4634340

Share

COinS