Can threshold networks be trained directly?
Top Cited Papers
- 13 March 2006
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing
- Vol. 53 (3) , 187-191
- https://doi.org/10.1109/tcsii.2005.857540
Abstract
Neural networks with threshold activation functions are highly desirable because of the ease of hardware implementation. However, the popular gradient-based learning algorithms cannot be directly used to train these networks as the threshold functions are nondifferentiable. Methods available in the literature mainly focus on approximating the threshold activation functions by using sigmoid functions. In this paper, we show theoretically that the recently developed extreme learning machine (ELM) algorithm can be used to train the neural networks with threshold functions directly instead of approximating them with sigmoid functions. Experimental results based on real-world benchmark regression problems demonstrate that the generalization performance obtained by ELM is better than other algorithms used in threshold networks. Also, the ELM method does not need control variables (manually tuned parameters) and is much faster.Keywords
This publication has 12 references indexed in Scilit:
- Extreme learning machine: a new learning scheme of feedforward neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Learning capability and storage capacity of two-hidden-layer feedforward networksIEEE Transactions on Neural Networks, 2003
- A learning algorithm for multi-layer perceptrons with hard-limiting threshold unitsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the networkIEEE Transactions on Information Theory, 1998
- Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functionsIEEE Transactions on Neural Networks, 1998
- Capabilities of a four-layered feedforward neural network: four layers versus threeIEEE Transactions on Neural Networks, 1997
- An iterative method for training multilayer networks with threshold functionsIEEE Transactions on Neural Networks, 1994
- Training binary node feedforward neural networks by back propagation of errorElectronics Letters, 1990
- Representing and learning Boolean functions of multivalued featuresIEEE Transactions on Systems, Man, and Cybernetics, 1990
- On the capabilities of multilayer perceptronsJournal of Complexity, 1988