Understanding human motion behavior is critical for autonomous moving platforms (like self-driving cars and social robots) if they are to navigate human-centric environments. This is challenging because human motion is inherently multimodal: given a history of human motion paths, there are many socially plausible ways that people could move in the future. We tackle this problem by combining too...

Triplet networks are widely used models that are characterized by good performance in classification and retrieval tasks. In this work we propose to train a triplet network by putting it as the discriminator in Generative Adversarial Nets (GANs). We make use of the good capability of representation learning of the discriminator to increase the predictive quality of the model. We evaluated our a...

The universal algebraic literature is rife with generalisations of discriminator varieties, whereby several investigators have tried to preserve in more general settings as much as possible of their structure theory. Here, we modify the definition of discriminator algebra by having the switching function project onto its third coordinate in case the ordered pair of its first two coordinates bel...

Generative adversarial networks (GANs) have demonstrated to be successful at generating realistic real-world images. In this paper we compare various GAN techniques, both supervised and unsupervised. The effects on training stability of different objective functions are compared. We add an encoder to the network, making it possible to encode images to the latent space of the GAN. The generator,...

A gel shift assay that distinguishes the aminoacylated form from the deacylated form of tRNAs was used to study the requirements for aminoacylation of Escherichia coli tRNA(Asn) in vivo. tRNA(Asn) derivatives containing single base changes in their anticodons or discriminator bases were constructed, and the extent of in vivo aminoacylation was determined directly. Substitution of U35 with C35 o...

Generative Adversarial Networks (GANs) have shown impressive performance in producing images highly similar to original dataset under unsupervised learning. However, the losses of discriminator and generator are highly fluctuated, which affects the quality of fake images produced by the generator. In this work, we propose Face Generative Adversarial Networks (FaceGANs). Compared to the conventi...

Generative Adversarial Networks (GANs) have recently been proposed as a promising avenue towards learning generative models with deep neural networks. While GANs have demonstrated state-of-the-art performance on multiple vision tasks, their learning dynamics are not yet well understood, both in theory and in practice. To address this issue, we take a first step towards a rigorous study of GAN d...

Generative Adversarial Networks (GANs), as a framework for estimating generative models via an adversarial process, have attracted huge attention and have proven to be powerful in a variety of tasks. However, training GANs is well known for being delicate and unstable, partially caused by its sigmoid cross entropy loss function for the discriminator. To overcome such a problem, many researchers...

The use of n-tuple or weightless neural networks as pattern recognition devices is well known (Aleksander and Stonham, 1979). They have some significant advantages over the more common and biologically plausible networks, such as multi-layer perceptrons; for example, n-tuple networks have been used for a variety of tasks, the most popular being real-time pattern recognition, and they can be imp...