Optoelectronic winner-take-all VLSI shunting neural network

1995 ◽  
Vol 6 (5) ◽  
pp. 1275-1279 ◽  
Author(s):  
J.S. Kane ◽  
T.G. Kincaid
Keyword(s):  
Neural Network ◽  
Winner Take All ◽  
Take All

Improved winner-take-all neural network

1992 ◽  
Vol 28 (7) ◽  
pp. 662 ◽  
Author(s):  
J.-C. Yen ◽  
S. Chang
Keyword(s):  
Neural Network ◽  
Winner Take All ◽  
Take All

Automatic Detection of Arrow Annotation Overlays in Biomedical Images

2011 ◽  
Vol 6 (4) ◽  
pp. 23-41 ◽  
Author(s):  
Beibei Cheng ◽  
R. Joe Stanley ◽  
Soumya De ◽  
Sameer Antani ◽  
George R. Thoma
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Computational Intelligence ◽  
Medical Images ◽  
Characteristic Curve ◽  
Data Set ◽  
Negative Correlation Learning ◽  
Artificial Neural ◽  
Winner Take All ◽  
Take All

Images in biomedical articles are often referenced for clinical decision support, educational purposes, and medical research. Authors-marked annotations such as text labels and symbols overlaid on these images are used to highlight regions of interest which are then referenced in the caption text or figure citations in the articles. Detecting and recognizing such symbols is valuable for improving biomedical information retrieval. In this research, image processing and computational intelligence methods are integrated for object segmentation and discrimination and applied to the problem of detecting arrows on these images. Evolving Artificial Neural Networks (EANNs) and Evolving Artificial Neural Network Ensembles (EANNEs) computational intelligence-based algorithms are developed to recognize overlays, specifically arrows, in medical images. For these discrimination techniques, EANNs use particle swarm optimization and genetic algorithm for artificial neural network (ANN) training, and EANNEs utilize the number of ANNs generated in an ensemble and negative correlation learning for neural network training based on averaging and Linear Vector Quantization (LVQ) winner-take-all approaches. Experiments performed on medical images from the imageCLEFmed’08 data set, yielded area under the receiver operating characteristic curve and precision/recall results as high as 0.988 and 0.928/0.973, respectively, using the EANNEs method with the winner-take-all approach.

A general mean-based iterative winner-take-all neural network

1995 ◽  
Vol 6 (1) ◽  
pp. 14-24 ◽  
Author(s):  
Jar-Ferr Yang ◽  
Chi-Ming Chen ◽  
Wen-Chung Wang ◽  
Jau-Yien Lee
Keyword(s):  
Neural Network ◽  
Winner Take All ◽  
Take All

A STRONG WINNER-TAKE-ALL NEURAL NETWORK IN ANALOGUE HARDWARE

1998 ◽  
pp. 178-190 ◽  
Author(s):  
R. MÖLLER ◽  
M. MARIS ◽  
J. TOMES ◽  
A. MOJAEV
Keyword(s):  
Neural Network ◽  
Winner Take All ◽  
Take All

Dynamics of a Winner-Take-All Neural Network

1996 ◽  
Vol 9 (7) ◽  
pp. 1141-1154 ◽  
Author(s):  
YUGUANG FANG ◽  
MICHAEL A. COHEN ◽  
THOMAS G. KINCAID
Keyword(s):  
Neural Network ◽  
Winner Take All ◽  
Take All

FAULT IMMUNIZATION CONCEPT FOR SELF-ORGANIZING MAPPING NEURAL NETWORKS

2001 ◽  
Vol 09 (06) ◽  
pp. 781-790 ◽  
Author(s):  
R. TALUMASSAWATDI ◽  
C. LURSINSAP
Keyword(s):  
Neural Network ◽  
Image Compression ◽  
Optimization Problem ◽  
Transmission Reliability ◽  
Real Value ◽  
Som Neural Network ◽  
Compression Area ◽  
Winner Take All ◽  
Take All ◽  
Self Organizing

Self-Organizing Mapping (SOM) neural network has been widely used in pattern classification, vector quantization, and image compression. We consider the problem of strengthening the reliability of a SOM neural network by the technique of fault immunization of the synaptic links of each neuron which is similar to the concept of biological immunization. Instead of assuming the stuck-at-0 and stuck-at-1 as in those studies, we consider a general case of stuck-at-a, where a is a real value. The only assumption that we consider is only one neuron can be faulty at any time. No restriction on the number of faulty links of the neuron. Let wi,j be the weight of synaptic link j of neuron i obtained after the winner-take-all classification. Weight wi,j is immunized by adding a constant ∊i,j, either positive or negative, to wi,j. A neuron reaches its maximum fault immunization if the value of wi,j + ∊i,j can be either increased or decreased as much as possible without creating any misclassification. Thus, the fault immunization problem is formulated as an optimization problem on finding the value of each ∊i,j. A technique to find the value of wi,j + ∊i,j is proposed and its application to enhance the transmission reliability in image compression area is introduced.

Sign in / Sign up

Export Citation Format

Share Document