XMLP: a Feed-Forward Neural Network with Two-Dimensional Layers and Partial Connectivity

Authors:
Antonio Canas;Eva M. Ortigosa;Antonio F. Díaz;Julio Ortega
Affiliations:
Dept. of Computer Architecture and Technology, ETS Ingeniería Informítica, University of Granada, Granada, Spain E-18071;Dept. of Computer Architecture and Technology, ETS Ingeniería Informítica, University of Granada, Granada, Spain E-18071;Dept. of Computer Architecture and Technology, ETS Ingeniería Informítica, University of Granada, Granada, Spain E-18071;Dept. of Computer Architecture and Technology, ETS Ingeniería Informítica, University of Granada, Granada, Spain E-18071
Venue:
IWANN '03 Proceedings of the 7th International Work-Conference on Artificial and Natural Neural Networks: Part II: Artificial Neural Nets Problem Solving Methods
Year:
2009

Citing 2
Cited 2

Application of Artificial Neural Networks to Chest Image Classification

IWANN '93 Proceedings of the International Workshop on Artificial Neural Networks: New Trends in Neural Computation
An Approach to Isolated Word Recognition Using Multilayer Perceptrons

IWANN '91 Proceedings of the International Workshop on Artificial Neural Networks

FPGA Implementation of a Perceptron-like Neural Network for Embedded Applications

IWANN '03 Proceedings of the 7th International Work-Conference on Artificial and Natural Neural Networks: Part II: Artificial Neural Nets Problem Solving Methods
Compact yet efficient hardware implementation of artificial neural networks with customized topology

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

This work presents an MLP-like feed-forward network with two-dimensional layers partially connected and other features, such as configurable activation functions and batched backpropagation with different smoothing-momentum alternatives. We name this model eXtended Multi-Layer Perceptron (XMLP) because it extends the connectivity of the MLP. Here we describe its architecture, the various activation functions that it can use, its learning algorithm, and the possible use of discretization intended for hardware implementation. We also show a configurable graphic tool developed to train and simulate any MLP-like network (totally or partially connected). Finally, we present some results on speech recognition in order to compare total and partial connectivity, as well as continuous and discrete operation.