Open Access. Powered by Scholars. Published by Universities.®

Digital Commons Network

Open Access. Powered by Scholars. Published by Universities.®

Articles 1 - 2 of 2

Full-Text Articles in Entire DC Network

Characterization Of A Class Of Sigmoid Functions With Applications To Neural Networks, Anil Ravindran Menon, Kishan Mehrotra, Chilukuri K. Mohan, Sanjay Ranka Jan 1996

Characterization Of A Class Of Sigmoid Functions With Applications To Neural Networks, Anil Ravindran Menon, Kishan Mehrotra, Chilukuri K. Mohan, Sanjay Ranka

College of Engineering and Computer Science - Former Departments, Centers, Institutes and Projects

Sigmoid functions, whose graphs are “S-shaped” curves, appear in a great variety of contexts, such as the transfer functions in many neural networks. Their ubiquity is no accident; these curves are among the simplest non-linear curves, striking a graceful balance between linear and non-linear behavior. .. This paper undertakes a study of two classes of sigmoids: the simple sigmoids, defined to be odd, asymptotically bounded, completely monotone functions in one variable, and the Hyperbolic sigmoids, a proper subset of simple sigmoids and a natural generalization of the hyperbolic tangent. The class of hyperbolic sigmoids includes a surprising number of well …


Tests Of Random Number Generators Using Ising Model Simulations, Paul D. Coddington Jan 1996

Tests Of Random Number Generators Using Ising Model Simulations, Paul D. Coddington

Northeast Parallel Architecture Center

Large-scale Monte Carlo simulations require high-quality random number generators to ensure correct results. The contrapositive of this statement is also true – the quality of random number generators can be tested by using them in large-scale Monte Carlo simulations. We have tested many commonly used random number generators with high precision Monte Carlo simulations of the 2-d Ising model using the Metropolis, Swendsen-Wang, and Wolff algorithms. This work is being extended to the testing of random number generators for parallel computers. The results of these tests are presented, along with recommendations for random number generators for high-performance computers, particularly for …