Self-creating and organizing neural networks

We have developed a self-creating and organizing unsupervised learning algorithm for artificial neural networks. In this study, we introduce SCONN and SCONN2 as two versions of self-creating and organizing neural network (SCONN) algorithms. SCONN creates an adaptive uniform vector quantizer (VQ), whereas SCONN2 creates an adaptive nonuniform VQ by neural-like architecture. SCONN's begin with only one output node, which has a sufficiently wide activation level, and the activation level decrease depending upon the time or the activation history. SCONN's decide automatically whether to adapt the weights of existing nodes or to create a new "son node." They are compared with two famous algorithms-the Kohonen's self organizing feature map (SOFM) (1988) as a neural VQ and the Linde-Buzo-Gray (LBG) algorithm (1980) as a traditional VQ. The results show that SCONN's have significant benefits over other algorithms.

[1]  Nariman Farvardin,et al.  Optimum quantizer performance for a class of non-Gaussian memoryless sources , 1984, IEEE Trans. Inf. Theory.

[2]  Paul L. Zador,et al.  Asymptotic quantization error of continuous signals and the quantization dimension , 1982, IEEE Trans. Inf. Theory.

[3]  Bart Kosko,et al.  Stochastic competitive learning , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[4]  J. Makhoul,et al.  Vector quantization in speech coding , 1985, Proceedings of the IEEE.

[5]  Jorma Laaksonen,et al.  Variants of self-organizing maps , 1990, International 1989 Joint Conference on Neural Networks.

[6]  Teuvo Kohonen.  Self-Organizing Feature Maps , 1988 .

[7]  Allen Gersho,et al.  Asymptotically optimal block quantization , 1979, IEEE Trans. Inf. Theory.

[8]  Robert M. Gray,et al.  Multiple local optima in vector quantizers , 1982, IEEE Trans. Inf. Theory.

[9]  Robert M. Gray,et al.  An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..