A Novel Constructive Neural Network Architecture Based on Improved Adaptive Learning Strategy for Pattern Classification

Constructive neural network algorithms provide optimal ways to determine the architecture of a multi layer perceptron network along with learning algorithms for determining appropriate weights for pattern classification problems. In this paper the possibility of developing a novel Constructive Neural Network architecture with improved adaptive learning strategy is proposed and analyzed. The new Multi category Tiling Constructive Neural Network architecture and the existing Tiling architecture are tested on machine learning datasets. The performance of the new learning strategy on Multi Category Tiling architecture was found to be comparatively better than when applied on the existing Tiling architecture.

[1]  DistAl: An inter-pattern distance-based constructive learning algorithm , 1999, Intell. Data Anal..

[2]  Estevam R. Hruschka,et al.  A Comparative Evaluation of Constructive Neural Networks Methods using PRM and BCP as TLU Training Algorithms , 2006, 2006 IEEE International Conference on Systems, Man and Cybernetics.

[3]  Timur Ash,et al.  Dynamic node creation in backpropagation networks , 1989 .

[4]  Leonardo Franco,et al.  Neural Network Architecture Selection: Can Function Complexity Help? , 2009, Neural Processing Letters.

[5]  M. Golea,et al.  A Convergence Theorem for Sequential Learning in Two-Layer Perceptrons , 1990 .

[6]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[7]  Emile Fiesler,et al.  Pruning of Neural Networks , 1997 .

[8]  J. Nadal,et al.  Learning in feedforward layered networks: the tiling algorithm , 1989 .

[9]  Marcus Frean,et al.  The Upstart Algorithm: A Method for Constructing and Training Feedforward Neural Networks , 1990, Neural Computation.

[10]  Alessio Micheli,et al.  Neural Network for Graphs: A Contextual Constructive Approach , 2009, IEEE Transactions on Neural Networks.

[11]  Leonardo Franco,et al.  Early Breast Cancer Prognosis Prediction and Rule Extraction Using a New Constructive Neural Network Algorithm , 2007, IWANN.

[12]  Xin Yao,et al.  A New Constructive Algorithm for Architectural and Functional Adaptation of Artificial Neural Networks , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[13]  Marcus R. Frean,et al.  A "Thermal" Perceptron Learning Rule , 1992, Neural Computation.

[14]  Russell Reed,et al.  Pruning algorithms-a survey , 1993, IEEE Trans. Neural Networks.

[15]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[16]  Rajesh Parekh,et al.  Constructive Neural Network Learning Algorithms for Multi-Category Real-Valued Pattern Classification , 1997 .

[17]  Perambur S. Neelakanta,et al.  INFORMATION-THEORETIC ASPECTS of NEURAL NETWORKS , 1999 .

[18]  Neil Burgess,et al.  A Constructive Algorithm that Converges for Real-Valued Input Patterns , 1994, Int. J. Neural Syst..

[19]  Catherine Blake,et al.  UCI Repository of machine learning databases , 1998 .

[20]  Jihoon Yang,et al.  Constructive Neural-Network Learning Algorithms for Pattern Classification , 2000 .

[21]  Fabio Massimo Frattale Mascioli,et al.  A constructive algorithm for binary neural networks: the oil-spot algorithm , 1995, IEEE Trans. Neural Networks.

[22]  Jihoon Yang,et al.  MUpstart-a constructive neural network learning algorithm for multi-category pattern classification , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[23]  Stephen I. Gallant,et al.  Perceptron-based learning algorithms , 1990, IEEE Trans. Neural Networks.