Automatic caption generation of an image requires both computer vision and natural language processing techniques. Despite of advanced research in English caption generation, research on generating Arabic descriptions of an image is extremely limited. Semitic languages like Arabic are heavily influenced by root-words. We leverage this critical dependency of Arabic and in this paper are the first to generate captions of an image directly in Arabic using root-word based Recurrent Neural Networks and Deep Neural Networks. We report the first BLEU score for direct Arabic caption generation. Experimental results confirm that generating image captions using root-words directly in Arabic significantly outperforms the English-Arabic translated captions using state-of-the-art methods.

Machine comprehension of text is the problem to answer a query based on a given context. Many existing systems use RNN-based units for contextual modeling linked with some attention mechanisms. In this paper, however, we propose StackReader, an end-to-end neural network model, to solve this problem, without recurrent neural network (RNN) units and its variants. This simple model is based solely on attention mechanism and gated convolutional neural network. Experiments on SQuAD have shown to have relatively high accuracy with a significant decrease in training time.

This abstract proposes a time series anomaly detector which 1) makes no assumption about the underlying mechanism of anomaly patterns, 2) refrains from the cumbersome work of threshold setting for good anomaly detection performance under specific scenarios, and 3) keeps evolving with the growth of anomaly detection experience. Essentially, the anomaly detector is powered by the Recurrent Neural Network (RNN) and adopts the Reinforcement Learning (RL) method to achieve the self-learning process. Our initial experiments demonstrate promising results of using the detector in network time series anomaly detection problems.

Visual recognition from very low-quality images is an extremely challenging task with great practical values. While deep networks have been extensively applied to low-quality image restoration and high-quality image recognition tasks respectively, few works have been done on the important problem of recognition from very low-quality images.This paper presents a degradation-robust pre-training approach on improving deep learning models towards this direction. Extensive experiments on different datasets validate the effectiveness of our proposed method.

With the advent of personal assistants such as Siri and Alexa, there has been a renewed focus on dialog systems, specifically open domain conversational agents. Dialog is a challenging problem since it spans multiple conversational turns. To further complicate the problem, there are many contextual cues and valid possible utterances. Dialog is fundamentally a multiscale process given that context is carried from previous utterances in the conversation; however, current neural methods lack the ability to carry human-like conversation. Neural dialog models are based on recurrent neural network Encoder-Decoder sequence-to-sequence models (Sutskever, Vinyals, and Le, 2014; Bahdanau, Cho, and Bengio, 2015). However, these models lack the ability to create temporal and stylistic coherence in conversations. We propose to incorporate dialog acts (such as Statement-non-opinion ["Me, I'm in the legal department."], Acknowledge ["Uh-huh."]) and discourse connectives (e.g. "because," "then"), utterance clustering and domain prediction, and style shifting using hierarchical methods. In particular, we show that clustering of utterance representations automatically allows for a unified hierarchical approach to discourse, domain, and style.

Cross-lingual Learning can help to bring state-of-the-art deep learning solutions to smaller languages. These languages in general lack resource for training advanced neural networks. With transfer of knowledge across languages we can improve the results for various NLP tasks.

The aim of this paper is to propose a new overarching challenge for AI: the design of imagination machines. Imagination has been defined as the capacity to mentally transcend time, place, and/or circumstance. Much of the success of AI currently comes from a revolution in data science, specifically the use of deep learning neural networks to extract structure from data. This paper argues for the development of a new field called imagination science, which extends data science beyond its current realm of learning probability distributions from samples. Numerous examples are given in the paper to illustrate that human achievements in the arts, literature, poetry, and science may lie beyond the realm of data science, because they require abilities that go beyond finding correlations: for example, generating samples from a novel probability distribution different from the one given during training; causal reasoning to uncover interpretable explanations; or analogical reasoning to generalize to novel situations (e.g., imagination in art, representing alien life in a distant galaxy, understanding a story about talking animals, or inventing representations to model the large-scale structure of the universe). We describe the key challenges in automating imagination, discuss connections between ongoing research and imagination, and outline why automation of imagination provides a powerful launching pad for transforming AI.

We present an foreground); show that rotation of the hand is arbitrary, the interactive, guided experimental activity which assumes no background may be uneven, lighting and subjects are heterogeneous background knowledge, during which the audience is introduced (adults and kids, male and female, different skin to supervised deep learning and some of its core concepts colors). in a learning-by-doing fashion. The activity consists in 3. In order to train a classifier, we need a training dataset, building from scratch a system that solves a challenging visual which we don't yet have: so we ask the audience to acquire pattern recognition task, namely classifying "rock paper it. We underline that for each picture they shoot we need scissors" hand gestures from pictures; the process encounters to know the class, and in practice we want to end up with unanticipated setbacks and challenges, which prompt three folders full of pictures, one for each.

Classifying products precisely and efficiently is a major challenge in modern e-commerce. The high traffic of new products uploaded daily and the dynamic nature of the categories raise the need for machine learning models that can reduce the cost and time of human editors. In this paper, we propose a decision level fusion approach for multi-modal product classification based on text and image neural network classifiers. We train input specific state-of-the-art deep neural networks for each input source, show the potential of forging them together into a multi-modal architecture and train a novel policy network that learns to choose between them. Finally, we demonstrate that our multi-modal network improves classification accuracy over both networks on a real-world large-scale product classification dataset that we collected from Walmart.com. While we focus on image-text fusion that characterizes e-commerce businesses, our algorithms can be easily applied to other modalities such as audio, video, physical sensors, etc.

NASA has acquired more than 22 million images from the planet Mars. To help users find images of interest, we developed a content-based search capability for Mars rover surface images and Mars orbital images. We started with the AlexNet convolutional neural network, which was trained on Earth images, and used transfer learning to adapt the network for use with Mars images. We report on our deployment of these classifiers within the PDS Imaging Atlas, a publicly accessible web interface, to enable the first content-based image search for NASA’s Mars images.