Neural network architecture selection: size depends on function complexity

Authors:
Iván Gómez;Leonardo Franco;José L. Subirats;José M. Jerez
Affiliations:
Departamento de Lenguajes y Ciencias de la Computación, Universidad de Málaga, Málaga, Spain;Departamento de Lenguajes y Ciencias de la Computación, Universidad de Málaga, Málaga, Spain;Departamento de Lenguajes y Ciencias de la Computación, Universidad de Málaga, Málaga, Spain;Departamento de Lenguajes y Ciencias de la Computación, Universidad de Málaga, Málaga, Spain
Venue:
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I
Year:
2006

Citing 12
Cited 1

The complexity of Boolean functions

The complexity of Boolean functions
What size net gives valid generalization?

Neural Computation
Depth-Size Tradeoffs for Neural Computation

IEEE Transactions on Computers - Special issue on artificial neural networks
Mining association rules between sets of items in large databases

SIGMOD '93 Proceedings of the 1993 ACM SIGMOD international conference on Management of data
Beyond market baskets: generalizing association rules to correlations

SIGMOD '97 Proceedings of the 1997 ACM SIGMOD international conference on Management of data
Automatic early stopping using cross validation: quantifying the criteria

Neural Networks
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Feedforward Neural Network Construction Using Cross Validation

Neural Computation
Generalization and Selection of Examples in Feedforward Neural Networks

Neural Computation
Role of function complexity and network size in the generalization ability of feedforward networks

IWANN'05 Proceedings of the 8th international conference on Artificial Neural Networks: computational Intelligence and Bioinspired Systems
Generalization properties of modular networks: implementing the parity function

IEEE Transactions on Neural Networks
The influence of oppositely classified examples on the generalization complexity of Boolean functions

IEEE Transactions on Neural Networks

Active Learning Using a Constructive Neural Network Algorithm

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

The relationship between generalization ability, neural network size and function complexity have been analyzed in this work. The dependence of the generalization process on the complexity of the function implemented by neural architecture is studied using a recently introduced measure for the complexity of the Boolean functions. Furthermore an association rule discovery (ARD) technique was used to find associations among subsets of items in the whole set of simulations results. The main result of the paper is that for a set of quasi-random generated Boolean functions it is found that large neural networks generalize better on high complexity functions in comparison to smaller ones, which performs better in low and medium complexity functions.