Generative Adversarial Networks (GANs) were intuitively and attractively explained under the perspective of game theory, wherein two involving parties are a discriminator and a generator. In this game, the task of the discriminator is to discriminate the real and generated (i.e., fake) data, whilst the task of the generator is to generate the fake data that maximally confuses the discriminator....

Nuclear and High Energy Physics experiments often deal with a large number of detectors. These detectors give out analog signals depicting several parameters like time of arrival, amplitude and width of these analog signals, and pulse count rate etc. Usually, fast discriminators are used to convert these analog signals to digital form, crossing a set threshold. We have designed and developed 8 ...

Image semantic completion is to employ remaining image information restore the damaged or missing areas. Face task usually more challenging than other inpainting problems as it requires stronger consistency. We proposed a contextual feature constrained DCGAN with paired discriminator inpaint face images, which capable of overcoming DCGAN's shortages insufficient learning capability and unstable...

We describe the structure of those locally finite varieties whose first order theory is decidable. A variety is a class of universal algebras defined by a set of equations. Such a class is said to be locally finite if every finitely generated member of the class is finite. It turns out that in order for such a variety to have a decidable theory it must decompose into the varietal product of thr...

[lo] H. Cramer and M. Leadbetter, “The moments of the number of [13] L. Ehrman, “Analysis of a zero-crossing frequency discriminator crossings of a level by a stationary normal process,” Ann. Math. with random inputs,” IEEE Trans. Aerospace and Navigational Stat., vol. 36, pp. 165661663, 1965. Electronics, vol. ANE-12, pp. 113-119, June 1965. [II] M. Loeve, Probability Theory. New York: Van Nos...

In this work, we present a method for unsupervised domain adaptation (UDA), where we aim to transfer knowledge from a label-rich domain (i.e., a source domain) to an unlabeled domain (i.e., a target domain). Many adversarial learning methods have been proposed for this task. These methods train domain classifier networks (i.e., a discriminator) to discriminate distinguish the features as either...