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
Citation
TENG, Teck-Hou; TAN, Zhong-Ming; and TAN, Ah-hwee.
Self-organizing neural models integrating rules and reinforcement learning. (2008). 2008 IEEE International Joint Conference on Neural Networks IJCNN: Hong Kong, June 1-8: Proceedings. 3771-3778.
Available at: https://ink.library.smu.edu.sg/sis_research/6556
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1109/IJCNN.2008.4634340