We present a new algorithm for finding low-complexity neural networks with high generalization capability. The algorithm searches for a "flat" minimum of the error function. A flat minimum is a large connected region in weight space where the error remains approximately constant. An MDL-based, Bayesian argument suggests that flat minima correspond to "simple" networks and low expected overfitti...

Conifers, a component of beauties of parks and landscapes, are infected with diverse pathogens, especially fungi. In this research, samples were collected from conifers displaying symptoms of disease in parks and landscapes of Rasht in Iran and for the isolation and identification of pathogenic fungi, pieces of infected tissues were placed in PDA and at the next stages in WA, PCA and SNA media ...

Smoothed analysis combines elements over worst-case and average case analysis. For an instance x, the smoothed complexity is the average complexity of an instance obtained from x by a perturbation. The smoothed complexity of a problem is the worst smoothed complexity of any instance. Spielman and Teng introduced this notion for continuous problems. We apply the concept to combinatorial problems...

Extended abstract. Many automatic speech recognition systems, which operate in a laboratory environment, achieve high recognition rates. As speech recognition has moved from the laboratory to the field, however, recognition scores drop significantly. Robust speech recognition refers to the problem of designing an automatic speech recogniser that works well in a wide range of unexpected or adver...

ABSTRACT The simplest models of dark matter halo formation rely on the heuristic assumption, motivated by spherical collapse, that virialized haloes originate from initial regions are maxima smoothed density field. Here, we replace this notion with dynamical requirement protohaloes be where local gravitational flow converges to a point. For purpose, look for spheres whose acceleration at bounda...