Border Pairs Method – Constructive MLP Learning Classification Algorithm
In this paper we present Border pairs method, a constructive learning algorithm for multilayer perceptron (MLP). During learning with this method a near-minimal network architecture is found. MLP learning is conducted separately by individual layers and neurons. The algorithm is tested in computer simulation with simple learning patterns (XOR and triangles image), with traditional learning patterns (Iris and MNIST) and with noisy learning patterns. During the learning we have less possibilities to get stuck in the local minima, generalization of learning is good. Learning with noisy, multi-dimensional and numerous learning patterns work well. The Border pairs method also supports incremental learning.
Keywordsartificial intelligence machine learning multilayer perceptron constructive neural network border pairs method (BPM)
Unable to display preview. Download preview PDF.
- 1.Alsmadi, M.S., Omar, K.B., Noah, S.A.: Back Propagation Algorithm: The Best Algorithm Among the Multi-layer Perceptron Algorithm. IJCSNS International Journal of Computer Science and Network Security 9(4) (2009)Google Scholar
- 2.do Carmo Nicoletti, M.: Constructive Neural Networks: Constructive Neural Network Algorithms for Feedforward Architectures Suitable for Classification Tasks. Springer, Berlin (2009)Google Scholar
- 3.Yang, J., Parekh, R., Honavar, V.: DistAl: An inter-pattern distance-based constructive learning algorithm. In: Intelligent Data Analysis, vol. 3, pp. 55–73. Elsevier, Amsterdam (1999)Google Scholar
- 5.Cortes, C., Vapnik, V.: Support-Vector Networks. Machine Learning 20 (1995)Google Scholar
- 6.Banerjee, A.: Initializing neural networks using decision trees. In: Computational learning theory and natural learning systems, vol. IV. MIT Press, Cambridge (1997)Google Scholar