No abstract

We investigate learning feature-to-feature translator networks by alternating back-propagation as a generalpurpose solution to zero-shot learning (ZSL) problems. It is a generative model-based ZSL framework. In contrast to models based on generative adversarial networks (GAN) or variational autoencoders (VAE) that require auxiliary networks to assist the training, our model consists of a single conditional generator that maps class-level semantic features and Gaussian white noise vector accounting for instance-level latent factors to visual features, and is trained by maximum likelihood estimation. The training process is a simple yet effective alternating backpropagation process that iterates the following two steps: (i) the inferential back-propagation to infer the latent factors of each observed example, and (ii) the learning backpropagation to update the model parameters. We show that, with slight modifications, our model is capable of learning from incomplete visual features for ZSL. We conduct extensive comparisons with existing generative ZSL methods on five benchmarks, demonstrating the superiority of our method in not only ZSL performance but also convergence speed and computational cost. Specifically, our model outperforms the existing state-of-the-art methods by a remarkable margin up to 3.1% and 4.0% in ZSL and generalized ZSL settings, respectively.

Podocyte number is significantly reduced in diabetic patients and animal models, but the mechanism remains unclear. In the present study, we found that high glucose induced apoptosis in control podocytes which express transient receptor potential canonical 6 (TRPC6) channels, but not in TRPC6 knockdown podocytes in which TRPC6 was knocked down by TRPC6 silencing short hairpin RNA (shRNA). This effect was reproduced by treatment of podocytes with the reactive oxygen species (ROS), hydrogen peroxide (H2O2). Single-channel data from cell-attached, patch-clamp experiments showed that both high glucose and H2O2 activated the TRPC6 channel in control podocytes, but not in TRPC6 knockdown podocytes. Confocal microscopy showed that high glucose elevated ROS in podocytes and that H2O2 reduced the membrane potential of podocytes and elevated intracellular Ca2+ via activation of TRPC6. Since intracellular Ca2+ overload induces apoptosis, H2O2-induced apoptosis may result from TRPC6-mediated elevation of intracellular Ca2+. These data together suggest that high glucose induces apoptosis in podocytes by stimulating TRPC6 via elevation of ROS.

We propose a new system for generating art. The system generates art by looking at art and learning about style; and becomes creative by increasing the arousal potential of the generated art by deviating from the learned styles. We build over Generative Adversarial Networks (GAN), which have shown the ability to learn to generate novel images simulating a given distribution. We argue that such networks are limited in their ability to generate creative products in their original design. We propose modifications to its objective to make it capable of generating creative art by maximizing deviation from established styles and minimizing deviation from art distribution. We conducted experiments to compare the response of human subjects to the generated art with their response to art created by artists. The results show that human subjects could not distinguish art generated by the proposed system from art generated by contemporary artists and shown in top art fairs.