论文信息 - S/sub -/ART: a modified ART 2-A algorithm with rapid intermediate learning capabilities

S/sub -/ART: a modified ART 2-A algorithm with rapid intermediate learning capabilities

A modification to the ART 2-A algorithm is presented, called S_ART, which speeds up ART 2-A in the intermediate learning case. By attaching a different learning rate to each output node, which is decreased through time according to the amount of learning the particular node has had, the required training-presentation time is significantly reduced, and thus a speedup of up to two orders of magnitude can be achieved. Learning-rate convergence can be "tweaked" by using a 'contribution' parameter which sets the lower-limiting value to which the learning rate decreases. An example of the clustering characteristics of the S_ART is given and compared to ART 2-A for rapid learning of hand-written signatures from a supplied database. Here, we use both S_ART and ART 2-A as ART/sub a/ networks in an ARTMAP system. The ART/sub b/ network is an ART 1 neural network.<<ETX>>

I. Taylor | M. Greenhough | M. Greenhough | I. Taylor

[1] Stephen Grossberg,et al. ART 3: Hierarchical search using chemical transmitters in self-organizing pattern recognition architectures , 1990, Neural Networks.

[2] Stephen Grossberg,et al. Art 2: Self-Organization Of Stable Category Recognition Codes For Analog Input Patterns , 1988, Other Conferences.

[3] John Pedersen,et al. Neural network signature verification using Haar wavelet and Fourier transforms , 1993, Other Conferences.

[4] Stephen Grossberg,et al. A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[5] Ian J. Taylor,et al. An Object Oriented ARTMAP System for Classifying Pitch , 1993, ICMC.

[6] Stephen Grossberg,et al. ART 2-A: an adaptive resonance algorithm for rapid category learning and recognition , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[7] Stephen Grossberg,et al. ARTMAP: supervised real-time learning and classification of nonstationary data by a self-organizing neural network , 1991, [1991 Proceedings] IEEE Conference on Neural Networks for Ocean Engineering.