Back propagation neural network is successfully used in various fields, particularly in pattern recognition. Despite numerous applications, back propagation neural network`s design and optimization are developed by trial-and-error process, which is time-consuming. On the other hand, although a dataset may contain many features, these features may not be useful in a back propagation neural netwo...

We consider the problem of reducing a potentially very large dataset to a subset of representative prototypes. Rather than searching over the entire space of prototypes, we first roughly divide the data into balanced clusters using bisecting k-means and spectral cuts, and then find the prototypes for each cluster by affinity propagation. We apply our algorithm to text data, where we perform an ...

Neural network, as a fundamental classification algorithm, is widely used in many image classification issues. With the rapid development of high performance computing device and parallel computing devices, convolutional neural network also draws increasingly more attention from many researchers in this area. In this project, we deduced the theory behind back-propagation neural network and impl...

Affinity propagation (AP) was recently introduced as an unsupervised learning algorithm for exemplar based clustering. In this paper novel text document clustering algorithm has been developed based on vector space model, phrases and affinity propagation clustering algorithm. Proposed algorithm can be called Phrase affinity clustering (PAC). PAC first finds the phrase by ukkonen suffix tree con...

In order to study the effect of R2O/Al2O3 (where R=Na or K), SiO2/Al2O3, Na2O/K2O and H2O/R2O molar ratios on the compressive strength (CS) of Metakaolin base geopolymers, more than forty data were gathered from literature. To increase the number of data, some experiments were also designed. The resulted data were utilized to train and test the three layer artificial neural network (ANN). Bayes...

We first formulate multiple targets tracking problem in a dynamic Markov network(DMN)which is derived from a MRFs for joint target state and a binary process for occlusion of dual adjacent targets. We then propose to embed a novel Particle based Belief Propagation algorithm into Markov Chain Monte Carlo approach (MCMC) to obtain the maximum a posteriori (MAP) estimation in the DMN. In the messa...

A two-stage iterative scheme is proposed to handle a central problem of molecular dynamics, the computation of interior eigenvalues of large Hamiltonian matrices. The proposed method involves an initial propagation process for a time-dependent wave operator which is then inserted in an iterative process (R.D.W.A. or S.C.M.) to yield the exact stationary wave operator. The merits of the wave ope...

John A. Hertz Nordita Blegdamsvej 17 2100 Copenhagen Denmark We introduce a cost function for learning in feed-forward neural networks which is an explicit function of the internal representation in addition to the weights. The learning problem can then be formulated as two simple perceptrons and a search for internal representations. Back-propagation is recovered as a limit. The frequency of s...

We propose a new exact Euclidean distance transformation (DT) by propagation, using bucket sorting. A fast but approximate DT is first computed using a coarse neighborhood. A sequence of larger neighborhoods is then used to gradually improve this approximation. Computations are kept short by restricting the use of these large neighborhoods to the tile borders in the Voronoi diagram of the image...