We report a high performance phase modulation direct detection microwave photonic link employing a photonic chip as a frequency discriminator. The photonic chip consists of five optical ring resonators (ORRs) which are fully programmable using thermo-optical tuning. In this discriminator a drop-port response of an ORR is cascaded with a through response of another ORR to yield a linear phase mo...

We present an image-conditional image generation model. The model transfers an input domain to a target domain in semantic level, and generates the target image in pixel level. To generate realistic target images, we employ the real/fake-discriminator as in Generative Adversarial Nets [6], but also introduce a novel domain-discriminator to make the generated image relevant to the input image. W...

In this paper we propose equipping Generative Adversarial Networks with the ability to produce direct energy estimates for samples. Specifically, we develop a flexible adversarial training framework, and prove this framework not only ensures the generator converges to the true data distribution, but also enables the discriminator to retain the density information at the global optimum. We deriv...

This paper presents a new method — adversarial advantage actor-critic (Adversarial A2C), which significantly improves the efficiency of dialogue policy learning in taskcompletion dialogue systems. Inspired by generative adversarial networks (GAN), we train a discriminator to differentiate responses/actions generated by dialogue agents from responses/actions by experts. Then, we incorporate the ...

Let /C be a class of (universal) algebras of fixed type. /C* denotes the class obtained by augmenting each member of K, by the ternary discriminator function (/(x,y, z) = x if x / ?/, ^(x,x,z) = 2:), while V(/C*) is the closure of /C* under the formation of subalgebras, homomorphic images, and arbitrary Cartesian products. For example, the class of Boolean algebras is definitionally equivalent ...

We introduce a simple semi-supervised learning approach for images based on in-painting using an adversarial loss. Images with random patches removed are presented to a generator whose task is to fill in the hole, based on the surrounding pixels. The in-painted images are then presented to a discriminator network that judges if they are real (unaltered training images) or not. This task acts as...

An analog phase discriminator, based on the two complementary CMOS switches, was proposed to measure the initial phase of the sinusoidal wave. The circuit structure of the phase discriminator and its principle were presented, and the phase computational formula was derived through a series of circuit theories. So the initial phase was acquired directly from the circuit, which covered a wide fre...

We study the following problem: Determine which almost structurally complete quasivarieties are structurally complete. We propose a general solution to this problem and then a solution in the semisimple case. As a consequence, we obtain a characterization of structurally complete discriminator varieties. An interesting corollary in logic follows: Let L be a propositional logic/deductive system ...

This paper presents a deep learning based approach to the problem of human pose estimation. We employ generative adversarial networks as our learning paradigm in which we set up two stacked hourglass networks with the same architecture, one as the generator and the other as the discriminator. The generator is used as a human pose estimator after the training is done. The discriminator distingui...

INTRODUCTION.The RATIO DETECTOR uses a double-tuned transformer to convert the instantaneous frequency variations of the fm input signal to instantaneous amplitude.AM version is shown at A to make it a CWSSB receiver, change the detector to a. 4An FM ratio detector of the type mentioned in the text. It is similar to the.Ratio detector or discriminator was widely used for FM demodulation within ...