It is known that training deep neural networks, in particular, deep convolutional networks, with aggressively reduced numerical precision is challenging. The stochastic gradient descent algorithm becomes unstable in the presence of noisy gradient updates resulting from arithmetic with limited numeric precision. One of the wellaccepted solutions facilitating the training of low precision fixed p...

In peer-to-peer (p2p) networks, peer nodes communicate with each other with the help of overlay structure. As the peers in the p2p system join and leave the network randomly, it makes the overlay network dynamic and unstable in nature. In this paper, we propose an analytical framework to assess the robustness of different topologies adopted by these overlay structures, to withstand the random m...

Background: Unstable angina and myocardial infarction are developed due to atherosclerosis of coronary arteries. At present, cholestrol, triglyceride, and lipoproteins are the most common risk factors of death. The purpose of this study was to assess the serum levels of LP (a), LDL-C, VLDL-C, HDL-C in cases of unstable angina and myocardial infarction.Methods: This study was conducted to compar...

It is often assumed that learning takes place by changing an otherwise stable neural representation. To test this assumption, we studied changes in the directional tuning of primate motor cortical neurons during reaching movements performed in familiar and novel environments. During the familiar task, tuning curves exhibited slow random drift. During learning of the novel task, random drift was...

Previous explanations of computations performed by recurrent networks have focused on symmetrically connected saturating neurons and their convergence toward attractors. Here we analyze the behavior of asymmetrical connected networks of linear threshold neurons, whose positive response is unbounded. We show that, for a wide range of parameters, this asymmetry brings interesting and computationa...

The stochastic shortest path length is defined as the arrival probability from a given source node to a given destination node in the stochastic networks. We consider the topological changes and their effects on the arrival probability in directed acyclic networks. There is a stable topology which shows the physical connections of nodes; however, the communication between nodes does not stable ...

We consider a ring of identical neurons with delayed nearest neighborhood inhibitory interaction. Under general conditions, such a network has a slowly oscillatory synchronous periodic solution which is completely characterized by a scalar delay differential equation with negative feedback. Despite the fact that the slowly oscillatory periodic solution of the scalar equation is stable, we show ...