Competitive Learning with Fast Neuron-Insertion
Noritaka Shigei*, Hiromi Miyajima*, and Michiharu Maeda**
*Kagoshima University, Kagoshima-shi 890-0065, Japan
**Kurume National College of Technology, Kurume-shi 830-8555, Japan
Received:February 25, 2005Accepted:June 12, 2005Published:November 20, 2005
Keywords:adaptive vector quantization, competitive learning, neuron-insertion,computational cost, image compression
Adaptive Vector Quantization (AVQ) is to find a small set of weight vectors that well approximates a larger set of input vectors. This paper presents a fast AVQ method Competitive Learning with Approximate Neuron-Insertion (CLANI). Though neuron-insertion techniques can much enhance the accuracy in AVQ, a naive implementation requires a large computational cost proportional to the number of input vectors. Approximate neuron-insertion has an advantage that its computational cost is independent of the number of input vectors. We theoretically estimate the computational costs of CLANI and the other conventional methods. The effectiveness of CLANI is demonstrated in vector quantization simulations and an image compression application.
Cite this article as:N. Shigei, H. Miyajima, and M. Maeda, “Competitive Learning with Fast Neuron-Insertion,” J. Adv. Comput. Intell. Intell. Inform., Vol.9 No.6, pp. 590-598, 2005.Data files: