Chipmaker Intel has unveiled a new version of its neural networks plug-in device aimed at helping developers reach further into the domain of artificial intelligence learning and edge computing. The Neural Compute Stick 2 is effectively a USB stick containing the Movidius Myriad X Vision Processing Unit. The new unit is, in essence, a chip that performs eight times faster than previous stick versions, says Intel, and is designed to carry out accelerated computations related to computer vision and image recognition on network edge devices. Intel said the stick could be used to "prototype and deploy deep neural network applications smarter and more efficiently with a tiny, fanless, deep learning development kit designed to enable a new generation of intelligent devices." Developers insert the NCS 2 into a compatible USB 3.0 port on their computers and configure it with AI and computer vision know-how before slotting it into a smart device and testing its capabilities.

For humans, chess may take a lifetime to master. But Google DeepMind's new artificial intelligence program, AlphaZero, can teach itself to conquer the board in a matter of hours. Building on its past success with the AlphaGo suite--a series of computer programs designed to play the Chinese board game Go--Google boasts that its new AlphaZero achieves a level of "superhuman performance" at not just one board game, but three: Go, chess, and shogi (essentially, Japanese chess). The team of computer scientists and engineers, led by Google's David Silver, reported its findings recently in the journal Science. "Before this, with machine learning, you could get a machine to do exactly what you want--but only that thing," says Ayanna Howard, an expert in interactive computing and artificial intelligence at the Georgia Institute of Technology who did not participate in the research.

"Computer vision and machine learning have really started to take off, but for most people, the whole idea of what a computer is seeing when it's looking at an image is relatively obscure." The wonderful field of Computer Vision has soared into a league of it's own in recent years. There are an impressive number of applications already in wide use around the world – and we are just getting started! One of my favorite things in this field is the idea of our community embracing the concept of open source. Even the big tech giants are willing to share new breakthroughs and innovations with everyone so that the techniques do not remain a "thing of the rich".

Constant-curvature Riemannian manifolds (CCMs) have been shown to be ideal embedding spaces in many application domains, as their non-Euclidean geometry can naturally account for some relevant properties of data, like hierarchy and circularity. In this work, we introduce the CCM adversarial autoencoder (CCM-AAE), a probabilistic generative model trained to represent a data distribution on a CCM. Our method works by matching the aggregated posterior of the CCM-AAE with a probability distribution defined on a CCM, so that the encoder implicitly learns to represent the data on the CCM in order to fool a discriminator network. The geometrical constraint is also explicitly imposed by jointly training the CCM-AAE to maximise the membership degree of the embeddings to the CCM. While several works in recent literature make use of either hyperspherical or hyperbolic manifolds for different learning tasks, ours is the first unified framework to seamlessly deal with CCMs of different curvatures. We show the effectiveness of our model on three different datasets characterised by non-trivial geometry: semi-supervised classification on MNIST, link prediction on two popular citation datasets, and graph-based molecule generation using the QM9 chemical database. Results show that our model compares favourably to other autoencoders based on Euclidean and non-Euclidean geometries on all tasks taken into account.

Deep Learning has been shown to learn efficient representations for structured data such as image, text or audio. In this chapter, we present neural network architectures that are able to learn efficient representations of molecules and materials. In particular, the continuous-filter convolutional network SchNet accurately predicts chemical properties across compositional and configurational space on a variety of datasets. Beyond that, we analyze the obtained representations to find evidence that their spatial and chemical properties agree with chemical intuition.

Machine translation (MT) is an area of study in Natural Language processing which deals with the automatic translation of human language, from one language to another by the computer. Having a rich research history spanning nearly three decades, Machine translation is one of the most sought after area of research in the linguistics and computational community. In this paper, we investigate the models based on deep learning that have achieved substantial progress in recent years and becoming the prominent method in MT. We shall discuss the two main deep-learning based Machine Translation methods, one at component or domain level which leverages deep learning models to enhance the efficacy of Statistical Machine Translation (SMT) and end-to-end deep learning models in MT which uses neural networks to find correspondence between the source and target languages using the encoder-decoder architecture. We conclude this paper by providing a time line of the major research problems solved by the researchers and also provide a comprehensive overview of present areas of research in Neural Machine Translation.

With the emergence of the Hospital Readmission Reduction Program of the Center for Medicare and Medicaid Services on October 1, 2012, forecasting unplanned patient readmission risk became crucial to the healthcare domain. There are tangible works in the literature emphasizing on developing readmission risk prediction models; However, the models are not accurate enough to be deployed in an actual clinical setting. Our study considers patient readmission risk as the objective for optimization and develops a useful risk prediction model to address unplanned readmissions. Furthermore, Genetic Algorithm and Greedy Ensemble is used to optimize the developed model constraints.

Due to the recent advances in the area of deep learning, it has been demonstrated that a deep neural network, trained on a huge amount of data, can recognize cardiac arrhythmias better than cardiologists. Moreover, traditionally feature extraction was considered an integral part of ECG pattern recognition; however, recent findings have shown that deep neural networks can carry out the task of feature extraction directly from the data itself. In order to use deep neural networks for their accuracy and feature extraction, high volume of training data is required, which in the case of independent studies is not pragmatic. To arise to this challenge, in this work, the identification and classification of four ECG patterns are studied from a transfer learning perspective, transferring knowledge learned from the image classification domain to the ECG signal classification domain. It is demonstrated that feature maps learned in a deep neural network trained on great amounts of generic input images can be used as general descriptors for the ECG signal spectrograms and result in features that enable classification of arrhythmias. Overall, an accuracy of 97.23 percent is achieved in classifying near 7000 instances by ten-fold cross validation.

To address Task 5 in the Detection and Classification of Acoustic Scenes and Events (DCASE) 2018 challenge, in this paper, we propose an ensemble learning system. The proposed system consists of three different models, based on convolutional neural network and long short memory recurrent neural network. With extracted features such as spectrogram and mel-frequency cepstrum coefficients from different channels, the proposed system can classify different domestic activities effectively. Experimental results obtained from the provided development dataset show that good performance with F1-score of 92.19% can be achieved. Compared with the baseline system, our proposed system significantly improves the performance of F1-score by 7.69%.

Air quality forecasting has been regarded as the key problem of air pollution early warning and control management. In this paper, we propose a novel deep learning model for air quality (mainly PM2.5) forecasting, which learns the spatial-temporal correlation features and interdependence of multivariate air quality related time series data by hybrid deep learning architecture. Due to the nonlinear and dynamic characteristics of multivariate air quality time series data, the base modules of our model include one-dimensional Convolutional Neural Networks (CNN) and Bi-directional Long Short-term Memory networks (Bi-LSTM). The former is to extract the local trend features and the latter is to learn long temporal dependencies. Then we design a jointly hybrid deep learning framework which based on one-dimensional CNN and Bi-LSTM for shared representation features learning of multivariate air quality related time series data. The experiment results show that our model is capable of dealing with PM2.5 air pollution forecasting with satisfied accuracy.