| This paper describes several algorithms, mapping the back propagation learning algorithm onto a large 2-D torus architecture. To obtain high speedup, we have suggested an approach to combine the possible parallel aspects (training set parallelism, node parallelism and pipelining of training patterns) of the algorithm. Several algorithms were implemented on a 512 processor Fujitsu AP1000 and c...

The Quantified Constraint Satisfaction Problem (QCSP) has been introduced to express situations in which we are not able to control the value of some of the variables (the universal ones). Despite the expressiveness of QCSP, many problems, such as two-players games or motion planning of robots, remain difficult to express. Two more modeler-friendly frameworks have been proposed to handle this d...

Back propagation training algorithms have been implemented by many researchers for their own purposes and provided publicly on the internet for others to use in veriication of published results and for reuse in unrelated research projects. Often, the source code of a package is used as the basis for a new package for demonstrating new algorithm variations, or some functionality is added speciic...

We report on a technique for the computation of color edge maps using Hering's Color Space for color coding, and quasiranges, for edge detection. A suitable combination of the resulting edge maps gives an image that is a meaningful visual approximation to the original image. Being an edge map, storage in a small memory space is possible. Finally, a study on the performance depending on the thre...

Recent progress on many imaging and vision tasks has been driven by the use of deep feed-forward neural networks, which are trained by propagating gradients of a loss defined on the final output, back through the network up to the first layer that operates directly on the image. We propose back-propagating one step further—to learn camera sensor designs jointly with networks that carry out infe...

We describe a new method for recognizing humans by their gait using back propagation neural network(BPNN), BPNN algorithm is used to recognize humans by their gait patterns. Automatic gait recognition using Fourier descriptors and independent component analysis (ICA) for the purpose of human identification at a distance. Firstly, a simple background generation algorithm is introduced to subtrac...

We propose a new method for training iterative collective classifiers for labeling nodes in network data. The iterative classification algorithm (ICA) is a canonical method for incorporating relational information into the classification process. Yet, existing methods for training ICA models rely on computing relational features using the true labels of the nodes. This method introduces a bias ...

Image deblurring is the process of obtaining the original image by using the knowledge of the degrading factors. Degradation comes in many forms such as blur, noise, and camera misfocus. A major drawback of existing restoration methods for images is that they suffer from poor convergence properties; the algorithms converge to local minima, that they are impractical for real imaging applications...

This paper is concerced with the use of error back-propagation in phonetic classification. Our objective is to investigate the basic characteristics of back-propagation, and study how the framework of multi-layer perceptrons can be exploited in phonetic recognition. We explore issues such as integration of heterogeneous sources of information, conditioll~ that can affect performance of phonetic...