An incremental probabilistic neural network for regression and reinforcement learning tasks

Authors:
Milton Roberto Heinen;Paulo Martins Engel
Affiliations:
UFRGS, Informatics Institute, Porto Alegre, RS, Brazil;UFRGS, Informatics Institute, Porto Alegre, RS, Brazil
Venue:
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part II
Year:
2010

Citing 10
Cited 2

Probabilistic neural networks

Neural Networks
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Fuzzy Probabilistic Neural Networks: A Practical Approach to the Implementation of Baysian Classifier

Proceedings of the International Conference, 7th Fuzzy Days on Computational Intelligence, Theory and Applications
Making reinforcement learning work on real robots

Making reinforcement learning work on real robots
Introduction to Data Mining, (First Edition)

Introduction to Data Mining, (First Edition)
Probabilistic Robotics (Intelligent Robotics and Autonomous Agents)

Probabilistic Robotics (Intelligent Robotics and Autonomous Agents)
Reinforcement Learning in Continuous Time and Space

Neural Computation
FPGA implementation of a General Regression Neural Network: An embedded pattern classification system

Digital Signal Processing
Incremental learning of multivariate Gaussian mixture models

SBIA'10 Proceedings of the 20th Brazilian conference on Advances in artificial intelligence
Adaptive probabilistic neural networks for pattern classification in time-varying environment

IEEE Transactions on Neural Networks

Concept formation using incremental Gaussian mixture models

CIARP'10 Proceedings of the 15th Iberoamerican congress conference on Progress in pattern recognition, image analysis, computer vision, and applications
Probabilistic neural network with homogeneity testing in recognition of discrete patterns set

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a new probabilistic neural network model, called IPNN (for Incremental Probabilistic Neural Network), which is able to learn continuously probability distributions from data flows. The proposed model is inspired by the Specht's general regression neural network, but have several improvements which makes it more suitable to be used on-line in and robotic tasks. Moreover, IPNN is able to automatically define the network structure in an incremental way, with new units added whenever necessary to represent new training data. The performed experiments shows that IPNN is very useful in regression and reinforcement learning tasks.