文章基本信息

标题：IGMN: An incremental connectionist approach for concept formation, reinforcement learning and robotics
本地全文：下载
作者：Milton Roberto Heinen ; Paulo Martins Engel
期刊名称：Journal of Applied Computing Research
印刷版ISSN：2236-8434
出版年度：2011
卷号：1
期号：1
页码：2-19
语种：English
出版社：Journal of Applied Computing Research
摘要：This paper demonstrates the use of a new connectionist approach, called IGMN (standing for Incremental Gaussian Mixture Network) in some state-of-the-art research problems such as incremental concept formation, reinforcement learning and robotic mapping. IGMN is inspired on recent theories about the brain, especially the Memory-Prediction Framework and the Constructivist Artificial Intelligence, which endows it with some special features that are not present in most neural network models such as MLP, RBF and GRNN. Moreover, IGMN is based on strong statistical principles (Gaussian mixture models) and asymptotically converges to the optimal regression surface as more training data arrive. Through several experiments using the proposed model it is also demonstrated that IGMN learns incrementally from data flows (each data can be immediately used and discarded), it is not sensible to initialization conditions, does not require fine-tuning its configuration parameters and has a good computational performance, thus allowing its use in real time control applications. Therefore, IGMN is a very useful machine learning tool for concept formation and robotic tasks. Key words: Artificial neural networks, Bayesian methods, concept formation, incremental learning, Gaussian mixture models, autonomous robots, reinforcement learning.