We present a state-of-the-art image recognition system, Deep Image, developed using endto-end deep learning. The key components are a custom-built supercomputer dedicated to deep learning, a highly optimized parallel algorithm using new strategies for data partitioning and communication, larger deep neural network models, novel data augmentation approaches, and usage of multi-scale high-resolut...

Monodisperse cadmium sulphide (CdS) quantum dots (QDs) with a tunable size from 1.4 to 4.3 nm were synthesized by a non-injection method, and their surface states were characterized by photoluminescence spectroscopy and X-ray Photoelectron Spectroscopy (XPS). The steady state photoluminescence study identified that the proportion of the trap state emission increased with the QD size decrease, w...

We methodologically address the problem of Qvalue overestimation in deep reinforcement learning to handle high-dimensional state spaces efficiently. By adapting concepts from information theory, we introduce an intrinsic penalty signal encouraging reduced Q-value estimates. The resultant algorithm encompasses a wide range of learning outcomes containing deep Q-networks as a special case. Differ...

Nonnegative Matrix Factorization (NMF) is a widely used technique for data representation. Inspired by the expressive power of deep learning, several NMF variants equipped with deep architectures have been proposed. However, these methods mostly use the only nonnegativity while ignoring task-specific features of data. In this paper, we propose a novel deep approximately orthogonal nonnegative m...

Software frameworks for neural networks play key roles in the development and application of deep learning methods. However, as new types of deep learning models are developed, existing frameworks designed for convolutional neural networks are becoming less useful. In this paper, we introduce Chainer, a Pythonbased, standalone open source framework for deep learning models. Chainer provides a f...

The detection of emotions in textual data lets us discover more about the writer. The automatic detection of emotions is useful in a large amount of applications. Furthermore, new developments in deep learning have made it effective in more domains. This research combines the two areas and explores a deep learning method for emotional analysis. The method is benchmarked against current methods ...

We propose a deep learning method for single image superresolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural network (CNN) [15] that takes the lowresolution image as the input and outputs the high-resolution one. We further show that traditional sparse-coding-based SR methods can also ...

The Gafsa mining basin district in Southwestern Tunisia is one of the most important producers of phosphate in the world. The exploitation of this district started at the beginning of the twentieth century a few years after the first discovery of this valuable resource. The over-exploitation of groundwater to wash the phosphate caused water-level decline in the main aquifers and the corollaries...