The emerging edge computing has promoted immense interests in compacting a neural network without sacrificing much accuracy. In this regard, low-rank tensor decomposition constitutes a powerful tool to compress convolutional neural networks (CNNs) by decomposing the 4-way kernel tensor into multi-stage smaller ones. Building on top of Tucker-2 decomposition, we propose a generalized Higher Order Tucker Articulated Kernels (HOTCAKE) scheme comprising four steps: input channel decomposition, guided Tucker rank selection, higher order Tucker decomposition and fine-tuning. By subjecting each CONV layer to HOTCAKE, a highly compressed CNN model with graceful accuracy trade-off is obtained. Experiments show HOTCAKE can compress even pre-compressed models and produce state-of-the-art lightweight networks.

Chris Smith and Phil Sansom delve into the world of artificial Intelligence (AI) to find out how this emerging technology is changing the way we practise medicine... Mike - I think this is an area where AI stands a really good chance of making quite dramatic improvements to very large numbers of people's lives. Carolyn - Save lives and reduce medical complications. Beth - That's a concern - when machine-learning algorithms learn the wrong things. Andrew - Frankly revolutionary productivity that we are now starting to see from these AI approaches in drug design. Lee - It will replace all manual labor in all research laboratories. And then suddenly everyone can collaborate. Phil - But what was previously sci-fi is now closer to reality. AI technology exists, and there's a brand new frontier where it's being applied to the world of healthcare. Chris - But this isn't the AI you see in the movies. In the words of Kent University computer scientist Colin Johnson, "this is more software than Schwarzeneggar"... Colin - When scientists say AI, they often mean some piece of code that's running on a computer and it's taking some inputs.

More than 1,000 students are vying for places at the world's first dedicated artificial intelligence university in Abu Dhabi. The Mohamed bin Zayed University of Artificial Intelligence will swing open its doors in August, with demand high from those eager to be part of the inaugural class of 2020. The graduate-level institute revealed the bumper number of applicants are currently being put through a stringent vetting process ahead of the landmark opening term. Masters and PhD courses will be held at the forward-thinking seat of learning, which has cast the net far and wide across the globe in search of top talent. World's first artificial intelligence university to open in Abu Dhabi Artificial intelligence isn't coming to the UAE - it is already here During the university's first advisory board meeting, Dr Sultan Al Jaber, Minister of State, said the first wave of students would be at the forefront of a new era of innovation in the country.

Artificial intelligence-powered technologies are increasingly being used to help contain the novel coronavirus outbreak in China, with several tech companies tweaking their facial recognition algorithms to identify people who are wearing masks. Enterprises that use facial recognition for access control and attendance system needed to make the tweaks as traditional algorithms may not be sufficient for recognition. For, masks used by the employees often cover some features of the face. Beijing-based tech company Hanwang Technology Co Ltd has upgraded its core algorithm and introduced a new facial recognition system for those who wear masks. Huang Lei, vice-president of the company, said Hanwang Tech took just a month to develop the upgraded version.

Higher-order Recurrent Neural Networks (RNNs) are effective for long-term forecasting since such architectures can model higher-order correlations and long-term dynamics more effectively. However, higher-order models are expensive and require exponentially more parameters and operations compared with their first-order counterparts. This problem is particularly pronounced in multidimensional data such as videos. To address this issue, we propose Convolutional Tensor-Train Decomposition (CTTD), a novel tensor decomposition with convolutional operations. With CTTD, we construct Convolutional Tensor-Train LSTM (Conv-TT-LSTM) to capture higher-order space-time correlations in videos. We demonstrate that the proposed model outperforms the conventional (first-order) Convolutional LSTM (ConvLSTM) as well as the state-of-the-art ConvLSTM-based approaches in pixel-level video prediction tasks on Moving-MNIST and KTH action datasets, but with much fewer parameters.

Delusional bias is a fundamental source of error in approximate Q-learning. To date, the only techniques that explicitly address delusion require comprehensive search using tabular value estimates. In this paper, we develop efficient methods to mitigate delusional bias by training Q-approximators with labels that are "consistent" with the underlying greedy policy class. We introduce a simple penalization scheme that encourages Q-labels used across training batches to remain (jointly) consistent with the expressible policy class. We also propose a search framework that allows multiple Q-approximators to be generated and tracked, thus mitigating the effect of premature (implicit) policy commitments. Experimental results demonstrate that these methods can improve the performance of Q-learning in a variety of Atari games, sometimes dramatically.

Able to monitor multiple patients in separate rooms simultaneously; staying on top of their blood pressure, pulse and vital signs; and spotting signs of deterioration even before the patients feel it themselves. This medical superhero is not human, but rather a product of artificial intelligence, advanced software algorithms, sensors and cameras. And it's being assembled right now at Tel Aviv Sourasky Medical Center. The creation of an AI-powered "super nurse" is the result of a decade of steady work by Ahuva Weiss-Meilik and her team in the hospital's I-Medata center. "Our doctors and nurses can't be everywhere," Weiss-Meilik tells ISRAEL21c.

Sci-fi movies have created an impact on our minds that using robots in our life is a very bad idea. From The Terminator to The Matrix, almost every Hollywood movie shows that robots took control over humanity. Even RUR, the 1920s Karel Capek play introduced the term "robot,". Despite the cinematic warnings robots have moved from fiction stories to an important piece of modern world arsenal. Now the developed world is also debating on the point to use develop killer robots and machine to save human life. In 1960, a company started building something that meets the guidelines of making a robot, that's when SRI International in Silicon Valley developed first truly perceptive and mobile robot known as SHAKY.

The paper surveys the topic of tensor decompositions in modern machine learning applications. It focuses on three active research topics of significant relevance for the community. After a brief review of consolidated works on multi-way data analysis, we consider the use of tensor decompositions in compressing the parameter space of deep learning models. Lastly, we discuss how tensor methods can be leveraged to yield richer adaptive representations of complex data, including structured information. The paper concludes with a discussion on interesting open research challenges.

Particulate matter pollution is one of the deadliest types of air pollution worldwide due to its significant impacts on the global environment and human health. Particulate Matter (PM2.5) is one of the important particulate pollutants to measure the Air Quality Index (AQI). The conventional instruments used by the air quality monitoring stations to monitor PM2.5 are costly, bulkier, time-consuming, and power-hungry. Furthermore, due to limited data availability and non-scalability, these stations cannot provide high spatial and temporal resolution in real-time. To overcome the disadvantages of existing methodology this article presents analytical equations based prediction approach for PM2.5 using an Artificial Neural Network (ANN). Since the derived analytical equations for the prediction can be computed using a Wireless Sensor Node (WSN) or low-cost processing tool, it demonstrates the usefulness of the proposed approach. Moreover, the study related to correlation among the PM2.5 and other pollutants is performed to select the appropriate predictors. The large authenticate data set of Central Pollution Control Board (CPCB) online station, India is used for the proposed approach. The RMSE and coefficient of determination (R2) obtained for the proposed prediction approach using eight predictors are 1.7973 ug/m3 and 0.9986 respectively. While the proposed approach results show RMSE of 7.5372 ug/m3 and R2 of 0.9708 using three predictors. Therefore, the results demonstrate that the proposed approach is one of the promising approaches for monitoring PM2.5 without power-hungry gas sensors and bulkier analyzers.