Besides their topological properties, Kohonen maps are often used for vector quantization only. These auto-organised networks are often compared to other standard and/or adaptive vector quantization methods, and, according to the large literature on the subject, show either better or worst properties in terms of quantization, speed of convergence, approximation of probability densities, cluster...

Besides their topological properties, Kohonen maps are often used for vector quantization only. These auto-organised networks are often compared to other standard and/or adaptive vector quantization methods, and, according to the large literature on the subject, show either better or worst properties in terms of quantization, speed of convergence, approximation of probability densities, cluster...

Stacked Auto-Encoder (SAE) is a kind of deep learning algorithm for unsupervised learning. Which has multilayers that project the vector representation of input data into a lower vector space. These projection vectors are dense representations of the input data. As a result, SAE can be used for image compression. Using chaotic logistic map, the compression ones can further be encrypted. In this...

Different (not only by sign) affine connections are introduced for con-travariant and covariant tensor fields over a differentiable manifold by means of a non-canonical contraction operator, defining the notion dual space and commuting with the covariant and with the Lie-differential operator. Classification of the linear transports on the basis of the connections between the connections is giv...

considering the importance of government fiscal policy (government spending and state tax income) in economy and its effectiveness in well-being of people, this paper examines the effects of fiscal policy on poverty during the period 1386-1363 in iran. in this paper, considering the fact that poverty changes can be divided to changes in economic growth and changes in income distribution; initia...

the six-degree equations of flight in their classic form do not provide a proper physical perception due to a number of interferences. nor do they render visible the important role of attack angles. in this study, attempts have been made to develop a complete set of 3d acceleration equations from the equations of normal and tangential acceleration αn=vωv, αt=v ̇. for this purpose, a coordinate s...

This paper suggests an optimisation method to design multi-band antenna using artificial neural networks. The proposed network, surrogate-based model auto-encoder (SBM-AE), is composed of two parts, ordinary network and auto-encoder. First, the front predicts encoded characteristics then decodes predicted data obtain characteristics. After training encoder a characteristic signature vector, reg...