The feed forward neural network which is a model of the cerebral neural network has in-built fault tolerance. The conventional back-propagation algorithm reduces errors between the learning examples and the output of a multilayer neural network (MNN). However, it is not assured that the MNN behaves in the same manner when faults occur. For these reasons the study of fault tolerance in artificia...

The decisions made by admission control algorithms are based on the availability of network resources viz. bandwidth, energy, memory buffers, etc., without degrading the Quality-of-Service (QoS) requirement of applications that are admitted. In this paper, we present an energy-aware admission control (EAAC) scheme which provides admission control for flows in an ad hoc network based on the know...

In the title compound, [Mn(C(5)H(7)O(2))(2)(C(12)H(16)N(3)O(2))], the manganese(II) cation (site symmetry ) is hexa-coordinated by four O and two N atoms in a distorted trans-MnN(2)O(4) octa-hedral geometry. The four O atoms belonging to two 2,4-penta-nedionate anions lie in the equatorial plane and the two N atoms occupy the axial coordination sites.

Multilayer Neural Networks (MNNs) are commonly trained using gradient descent-based methods, such as BackPropagation (BP). Inference in probabilistic graphical models is often done using variational Bayes methods, such as Expectation Propagation (EP). We show how an EP based approach can also be used to train deterministic MNNs. Specifically, we approximate the posterior of the weights given th...

Network mobility (NEMO) basic support protocol maintains the connectivity when mobile router (MR) changes its point of attachment to the Internet by establishing a bidirectional tunnel between MR and Home Agent (HA). However, it results in pin-ball routing and multiple encapsulations especially in the nested NEMO. In order to solve these problems, we propose a simple route optimization scheme f...

Hyperspectral image (HSI) unmixing is an increasingly studied problem in various areas, including remote sensing. It has been tackled using both physical model-based approaches and more recently machine learning-based ones. In this article, we propose a new HSI algorithm combining model- techniques, based on unrolling approaches, delivering improved performance. Our approach unrolls the alterna...

Background: Statistical mechanics results (Dauphin et al. (2014); Choromanska et al. (2015)) suggest that local minima with high error are exponentially rare in high dimensions. However, to prove low error guarantees for Multilayer Neural Networks (MNNs), previous works so far required either a heavily modified MNN model or training method, strong assumptions on the labels (e.g., “near” linear ...

In this note, we develop fast and deterministic dimensionality reduction techniques for a family of subspace approximation problems. Let P ⊂ R be a given set of M points. The techniques developed herein find an O(n logM)-dimensional subspace that is guaranteed to always contain a near-best fit n-dimensional hyperplane H for P with respect to the cumulative projection error (∑ x∈P ‖x−ΠHx‖ p 2 )1...