On the computational power of sigmoid versus boolean threshold circuits (extended abstract)
SFCS '91 Proceedings of the 32nd annual symposium on Foundations of computer science
Knowledge-based artificial neural networks
Artificial Intelligence
Bounds for the Computational Power and Learning Complexity of Analog Neural Nets
SIAM Journal on Computing
A feature selection technique for classificatory analysis
Pattern Recognition Letters
Selective fusion of heterogeneous classifiers
Intelligent Data Analysis
Neural Solutions for High Range Resolution Radar Classification
IWANN '03 Proceedings of the 7th International Work-Conference on Artificial and Natural Neural Networks: Part II: Artificial Neural Nets Problem Solving Methods
Multilayer perceptrons applied to traffic sign recognition tasks
IWANN'05 Proceedings of the 8th international conference on Artificial Neural Networks: computational Intelligence and Bioinspired Systems
IEEE Transactions on Information Technology in Biomedicine
Fuzzy CoCo: a cooperative-coevolutionary approach to fuzzy modeling
IEEE Transactions on Fuzzy Systems
IEEE Transactions on Information Theory
Extracting M-of-N rules from trained neural networks
IEEE Transactions on Neural Networks
Subsethood-product fuzzy neural inference system (SuPFuNIS)
IEEE Transactions on Neural Networks
IEEE Transactions on Neural Networks
MUSP'09 Proceedings of the 9th WSEAS international conference on Multimedia systems & signal processing
Designing neural networks for tackling hard classification problems
WSEAS TRANSACTIONS on SYSTEMS
Hi-index | 0.00 |
The paper aims at tight upper bounds on the size of pattern classification circuits that can be used for a priori parameter settings in a machine learning context. The upper bounds relate the circuit size S(C) to nL := [log2mL], where mL is the number of training samples. In particular, we show that there exist unbounded fan-in threshold circuits with less than (a) SRcc := 2·√2nL + 3 gates for unbounded depth, (b) SLcc := 34.8 · √2nL + 14 · nL − 11 · log2nL + 2 gates for small bounded depth, where in both cases all mL samples are classified correctly. We note that the upper bounds do not depend on the length n of input (sample) vectors. Since nL Rcc or [0.07 · SLcc] gates are sufficient to achieve a high generalization rate of bounded-depth classification circuits.