Machine translation systems based on deep neural networks are expensive to train.
Recent deep learning approaches to single image super-resolution have achieved impressive results in terms of traditional error measures and perceptual quality.
Ranked #8 on Image Super-Resolution on Set14 - 4x upscaling
Common nonlinear activation functions used in neural networks can cause training difficulties due to the saturation behavior of the activation function, which may hide dependencies that are not visible to vanilla-SGD (using first order gradients only).
In this paper, we propose an image super-resolution feedback network (SRFBN) to refine low-level representations with high-level information.
Recurrent Neural Networks can be trained to produce sequences of tokens given some input, as exemplified by recent results in machine translation and image captioning.
Partially Observable Stochastic Games (POSGs), are the most general model of games used in Multi-Agent Reinforcement Learning (MARL), modeling actions and observations as happening sequentially for all agents.
As an emerging topic in face recognition, designing margin-based loss functions can increase the feature margin between different classes for enhanced discriminability.
Generative Adversarial Networks (GANs) have shown great promise recently in image generation.