As an indispensable component, Batch Normalization (BN) has successfully improved thetraining of deep neural networks (DNNs) with mini-batches, by normalizing the distribution of the internal representation for each hidden layer. However, the effectiveness of BN would diminish with the scenario of micro-batch (e.g. less than 4 samples in a mini-batch), since the estimated statistics in a mini-batch are not reliable with insufficient samples. This limits BN's room in training larger models on segmentation, detection, and video-related problems, which require small batches constrained by memory consumption. In this paper, we present a novel normalization method, called Kalman Normalization (KN), for improving and accelerating the training of DNNs, particularly under the context of microbatches. Specifically,unlike the existing solutions treating each hidden layer as an isolated system, KN treats all the layers in a network as a whole system, and estimates the statistics of a certain layer by considering the distributions of all its preceding layers, mimicking the merits of Kalman Filtering. On ResNet50 trained in ImageNet, KN has 3.4% lower error than its BN counterpart when using a batch size of 4; Even when using typical batch sizes, KN still maintains an advantage over BN while other BN variants suffer a performance degradation. Moreover, KN can be naturally generalized to many existing normalization variants to obtain gains, e.g.equipping Group Normalization [34] with Group Kalman Normalization (GKN). KN can outperform BN and its variants for large scale object detection and segmentation task in COCO 2017.

Indian Robotics company Emotix launched their advanced version of robot – Miko 2. Emotix is Mumbai City-based startup which has a solution for working parents who worried about kids care. Miko 2 is a companion robot for children. Miko 2 came 2 years after the Emotix company unveiled their first Miko Robot. The Miko 2 has advanced Artificial Intelligence, better parenting controls, front camera, microphones, and improved "Emotional Intelligence". Miko 2 is actually third product in its series.

Indian AI-powered software firm Staqu has revealed the launch of TRINETRA, an AI application for the Uttar Pradesh Police Department. The application digitizes and search records using AI and carries records of criminals, assisting police forces at ground zero with real-time information retrieval during investigations, regular checks, verifications, and at police checkpoints. The firm said the app is powered by Staqu's expertise in facial recognition, visual search, machine learning, and deep learning, works well with low-resolution images and videos, and offers better accuracy than any other criminal recognition system. "With AI-powered Gang identification Technology, TRIENETRA not only identifies a criminal but also their associates active in different districts and part of the states."

We may remember 2018 as a year in which great power rivalry materialized at the forefront of American strategy -- with emerging technologies as a critical dimension of this competition. At a time when divisive politics and intense partisanship have undermined solutions to even the most urgent policy dilemmas, there are reasons nonetheless for cautious optimism about the potential for progress on issues of technology, innovation and competition. The current advances in emerging technologies possess strategic significance in their own right, yet take on greater urgency because of this rivalry. Such new frontiers as biotechnology, artificial intelligence (AI), fifth-generation mobile communications (5G), and quantum computing are integral to economic competitiveness and are also the "very technologies that ensure we will be able to fight and win the wars of the future," according to the U.S. National Defense Strategy. Today, traditional American leadership is contested, as China emerges as a powerhouse in science and technology, with aspirations to become a global leader in innovation.

A week after China approved its first batch of video games in nine months, the list is finally available... and who's not included may be more notable than who is. The country's State Administration of Press, Publication, Radio, Film and Television has announced that 80 online games made the cut, but industry giant Tencent wasn't part of that initial mix. It's not certain why regulators didn't greenlight Tencent games, although China recently instituted an ethics committee that would ensure games don't promote addiction, short-sightedness and some forms of sex and violence. Although it has massively popular games like Arena of Valor (Honor of Kings in its home country) and involvement in both Fortnite and PUBG, it's still heavily dependent on releasing new games in its native China. Tencent's shares fell by more than 20 percent in 2018 due to the approvals freeze, and they're unlikely to recover now that an approval still isn't in the cards.

Knowledge bases (KB), both automatically and manually constructed, are often incomplete --- many valid facts can be inferred from the KB by synthesizing existing information. A popular approach to KB completion is to infer new relations by combinatory reasoning over the information found along other paths connecting a pair of entities. Given the enormous size of KBs and the exponential number of paths, previous path-based models have considered only the problem of predicting a missing relation given two entities or evaluating the truth of a proposed triple. Additionally, these methods have traditionally used random paths between fixed entity pairs or more recently learned to pick paths between them. We propose a new algorithm MINERVA, which addresses the much more difficult and practical task of answering questions where the relation is known, but only one entity. Since random walks are impractical in a setting with combinatorially many destinations from a start node, we present a neural reinforcement learning approach which learns how to navigate the graph conditioned on the input query to find predictive paths. Empirically, this approach obtains state-of-the-art results on several datasets, significantly outperforming prior methods.

Approximate computing is being considered as a promising design paradigm to overcome the energy and performance challenges in computationally demanding applications. If the case where the accuracy can be configured, the quality level versus energy efficiency or delay also may be traded-off. For this technique to be used, one needs to make sure a satisfactory user experience. This requires employing error predictors to detect unacceptable approximation errors. In this work, we propose a scheduling-aware feature selection method which leverages the intermediate results of the hardware accelerator to improve the prediction accuracy. Additionally, it configures the error predictors according to the energy consumption and latency of the system. The approach enjoys the flexibility of the prediction time for a higher accuracy. The results on various benchmarks demonstrate significant improvements in the prediction accuracy compared to the prior works which used only the accelerator inputs for the prediction.

Deep learning is a main focus of artificial intelligence and has greatly impacted other fields. However, deep learning is often criticized for its lack of interpretation. As a successful unsupervised model in deep learning, various autoencoders, especially convolutional autoencoders, are very popular and important. Since these autoencoders need improvements and insights, in this paper we shed light on the nonlinearity of a deep convolutional autoencoder in perspective of perfect signal recovery. In particular, we propose a new type of convolutional autoencoders, termed as Soft-Autoencoder (Soft-AE), in which the activations of encoding layers are implemented with adaptable soft-thresholding units while decoding layers are realized with linear units. Consequently, Soft-AE can be naturally interpreted as a learned cascaded wavelet shrinkage system. Our denoising numerical experiments on CIFAR-10, BSD-300 and Mayo Clinical Challenge Dataset demonstrate that Soft-AE gives a competitive performance relative to its counterparts.

Many applications in different domains produce large amount of time series data. Making accurate forecasting is critical for many decision makers. Various time series forecasting methods exist which use linear and nonlinear models separately or combination of both. Studies show that combining of linear and nonlinear models can be effective to improve forecasting performance. However, some assumptions that those existing methods make, might restrict their performance in certain situations. We provide a new Autoregressive Integrated Moving Average (ARIMA)-Artificial Neural Network(ANN) hybrid method that work in a more general framework. Experimental results show that strategies for decomposing the original data and for combining linear and nonlinear models throughout the hybridization process are key factors in the forecasting performance of the methods. By using appropriate strategies, our hybrid method can be an effective way to improve forecasting accuracy obtained by traditional hybrid methods and also either of the individual methods used separately.