Multilayer feedforward networks with adaptive spline activation function
- 1 May 1999
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 10 (3) , 672-683
- https://doi.org/10.1109/72.761726
Abstract
In this paper, a new adaptive spline activation function neural network (ASNN) is presented. Due to the ASNN's high representation capabilities, networks with a small number of interconnections can be trained to solve both pattern recognition and data processing real-time problems. The main idea is to use a Catmull-Rom cubic spline as the neuron's activation function, which ensures a simple structure suitable for both software and hardware implementation. Experimental results demonstrate improvements in terms of generalization capability and of learning speed in both pattern recognition and data processing tasks.Keywords
This publication has 22 references indexed in Scilit:
- Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networksPublished by Elsevier ,2003
- A feedforward neural network with function shape autotuningNeural Networks, 1996
- Approximation capability in C(R~/sup n/) by multilayer feedforward networks and related problemsIEEE Transactions on Neural Networks, 1995
- Regression modeling in back-propagation and projection pursuit learningIEEE Transactions on Neural Networks, 1994
- Approximations of continuous functionals by neural networks with application to dynamic systemsIEEE Transactions on Neural Networks, 1993
- A universal theorem on learning curvesNeural Networks, 1993
- Fast neural networks without multipliersIEEE Transactions on Neural Networks, 1993
- Statistical Theory of Learning Curves under Entropic Loss CriterionNeural Computation, 1993
- 30 years of adaptive neural networks: perceptron, Madaline, and backpropagationProceedings of the IEEE, 1990
- Oscillation and Chaos in Physiological Control SystemsScience, 1977