We formulate the entropy of a quantized artificial neural network as differentiable function that can be plugged regularization term into cost minimized by gradient descent. Our formulation scales efficiently beyond first order and is agnostic quantization scheme. The then trained to minimize parameters, so they optimally compressed via coding. experiment with our at quantizing compressing well...

We study the cross-entropy method for diffusions. One of the results is a versatile cross-entropy algorithm that can be used to design efficient importance sampling strategies for rare events or to solve optimal control problems. The approach is based on the minimization of a suitable cross-entropy functional, with a parametric family of exponentially tilted probability distributions. We illust...

We formalize the pair-wise registration problem in a maximum a posteriori (MAP) framework that employs a multinomial model of joint intensities with parameters for which we only have a prior distribution. To obtain an MAP estimate of the aligning transformation alone, we treat the multinomial parameters as nuisance parameters, and marginalize them out. If the prior on those is uninformative, th...

This study numerically investigated heat transfer and fluid flow characteristics in a novel cylindrical heat sink with helical minichannels for the laminar flow of fluid with temperature-dependent properties. A finite volume method was employed to obtain the solution of governing equations. The effects of helical angle, channel aspect ratio, and Reynolds number, which were regarded as main para...

Minimization problems involving @-entropyfunctionals (ageneralization of Boltzmann-Shannon entropy) are studied over a givenset A and a sequence of sets A, and the properties of their optimalsolutions I@,I,. Under certain conditions on the objective functional andthe sets A and A,, it is proven that as n increases to infinity, the optimalsolution I, converges in Llno...

In general, conventional error correction for inverse synthetic aperture radarimaging consists of range alignment and phase adjustment, which compensate range shift and phase error, respectively. Minimum entropy-based methods have been proposed to realize range alignment and phase adjustment. However, it becomes challenging to align high-resolution profiles when strong noise presents, even usin...

We present a comparison of error-based and entropybased methods for discretization of continuous features. Our study includes both an extensive empirical comparison as well as an analysis of scenarios where error minimization may be an inappropriate discretization criterion. We present a discretization method based on the C4.5 decision tree algorithm and compare it to an existing entropy-based ...

Entropy measures applied to time-frequency signal representations have been found to be reliable indicators of various signal’s features. This paper gives an introduction to the time-frequency signal analysis, emphasizing the properties of time-frequency distributions that allow the application of entropy measures to quantify signals complexity. The paper includes an overview of the key propert...