Sciweavers

NPL
2000
99views more  NPL 2000»
13 years 4 months ago
On the Internal Representations of Product Units
This paper explores internal representation power of product units [1] that act as the functional nodes in the hidden layer of a multi-layer feedforward network. Interesting proper...
Jung-Hua Wang, Yi-Wei Yu, Jia-Horng Tsai
NPL
2000
91views more  NPL 2000»
13 years 4 months ago
A Novel Self-Creating Neural Network for Learning Vector Quantization
This paper presents a novel self-creating neural network scheme which employs two resource counters to record network learning activity. The proposed scheme not only achieves the b...
Jung-Hua Wang, Chung-Yun Peng
NPL
2000
95views more  NPL 2000»
13 years 4 months ago
Bayesian Sampling and Ensemble Learning in Generative Topographic Mapping
Generative topographic mapping (GTM) is a statistical model to extract a hidden smooth manifold from data, like the self-organizing map (SOM). Although a deterministic search algo...
Akio Utsugi
NPL
2000
88views more  NPL 2000»
13 years 4 months ago
Learning Synaptic Clusters for Nonlinear Dendritic Processing
Nonlinear dendritic processing appears to be a feature of biological neurons and would also be of use in many applications of artificial neural networks. This paper presents a mod...
Michael W. Spratling, Gillian Hayes
NPL
2000
52views more  NPL 2000»
13 years 4 months ago
Associative Memories in Infinite Dimensional Spaces
Enrique Carlos Segura, Roberto P. J. Perazzo
NPL
2000
146views more  NPL 2000»
13 years 4 months ago
Competitive and Temporal Inhibition Structures with Spiking Neurons
The paper describes the implementation of competitive neural structures based on a spiking neural model that includes multiplicative or shunting synapses enabling non-saturated sta...
Eduardo Ros Vidal, Francisco J. Pelayo, P. Martin-...
NPL
2000
135views more  NPL 2000»
13 years 4 months ago
Towards the Optimal Learning Rate for Backpropagation
A backpropagation learning algorithm for feedforward neural networks with an adaptive learning rate is derived. The algorithm is based upon minimising the instantaneous output erro...
Danilo P. Mandic, Jonathon A. Chambers
NPL
2000
138views more  NPL 2000»
13 years 4 months ago
Neural Net Based Hybrid Modeling of the Methanol Synthesis Process
A Hybrid modeling approach, combining an analytical model with a radial basis function neural network is introduced in this paper. The modeling procedure is combined with genetic a...
Primoz Potocnik, Igor Grabec, Marko Setinc, Janez ...
NPL
2000
74views more  NPL 2000»
13 years 4 months ago
Coherent Response in a Chaotic Neural Network
Haruhiko Nishimura, Naofumi Katada, Kazuyuki Aihar...
NPL
2000
71views more  NPL 2000»
13 years 4 months ago
Learning with Permutably Homogeneous Multiple-Valued Multiple-Threshold Perceptrons
Alioune Ngom, Corina Reischer, Dan A. Simovici, Iv...