Abstract
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.
Highlights
Traditional artificial neural network (ANN) models, such as Multi-layer Perceptron (MLP) (Rumelhart et al, 1986), Radial Basis Functions (RBF) network (Powell, 1987) and General Regression Neural Network (GRNN) (Specht, 1991), are based on Cybernetics, a science devoted to understand the phenomena and natural processes through the study of communication and control in living organisms, machines and social processes (Ashby, 1956)
Neural networks can be successfully used in several tasks, including signal processing, pattern recognition and robotics, most ANN models have some disadvantages that difficult their use in on-line tasks such as incremental concept formation and robotics
The main goal of this paper is to present the application of IGMN in some practical tasks such as concept formation, reinforcement learning and robotic mapping, demonstrating that IGMN is a powerful machine learning tool that can be applied to many state-of-the-art computational and engineering problems
Summary
Traditional artificial neural network (ANN) models, such as Multi-layer Perceptron (MLP) (Rumelhart et al, 1986), Radial Basis Functions (RBF) network (Powell, 1987) and General Regression Neural Network (GRNN) (Specht, 1991), are based on Cybernetics, a science devoted to understand the phenomena and natural processes through the study of communication and control in living organisms, machines and social processes (Ashby, 1956). According to Cybernetics, the brain can be seen as an information system that receives information as input, performs some processing over this information and outcomes the computed results as output. In traditional connectionist models the information flow is unidirectional, from the input to the hidden layer (processing) and to the output layer (Pfeifer and Scheier, 1994). Neural networks can be successfully used in several tasks, including signal processing, pattern recognition and robotics, most ANN models have some disadvantages that difficult their use in on-line tasks such as incremental concept formation and robotics. After the end of the training process the synaptic weights are “frozen”, i.e., the network loses its learning capabilities.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.