We extend Generative Adversarial Networks (GANs) to the semi-supervised context by forcing the discriminator network to output class labels. We train a generative model G and a discriminator D on a dataset with inputs belonging to one of N classes. At training time, D is made to predict which of N+1 classes the input belongs to, where an extra class is added to correspond to the outputs of G. W...

The main focus of this work concerned with the development of integrated electronic and optoelectronic circuits and devices for pulsed time-of-flight laser rangefinding is on the construction of the receiver channel, system level integration aimed at realisation of the laser radar module and in integration of all the receiver functions of laser radar on one chip. Since the timing discriminator ...