Previous works observed the spectrum of the Hessian of the training loss of deep neural networks. However, the networks considered were of minuscule size. We apply state-of-the-art tools in modern high-dimensional numerical linear algebra to approximate the spectrum of the Hessian of deep nets with tens of millions of parameters. Our results corroborate previous findings, based on small-scale networks, that the Hessian exhibits 'spiked' behavior, with several outliers isolated from a continuous bulk. However we find that the bulk does not follow a simple Marchenko-Pastur distribution, as previously suggested, but rather a heavier-tailed distribution. Finally, we document the dynamics of the outliers and the bulk with varying sample size.

Learning using privileged information and distillation are powerful machine learning frameworks that allow a machine learning model to be learned from an existing model or from a classifier trained over another feature space. Existing implementations of learning using privileged information are limited to classification only. In this work, we have proposed a novel meta-loss function that allows the general application of learning using privileged information and distillation to not only classification but also regression and other related problems. Our experimental results show the usefulness of the proposed scheme.

Sparse Inverse Covariance Estimation (SICE) is useful in many practical data analyses. Recovering the connectivity, non-connectivity graph of covariates is classified amongst the most important data mining and learning problems. In this paper, we introduce a novel SICE approach using adaptive thresholding. Our method is based on updates in a transformed domain of the desired matrix and exponentially decaying adaptive thresholding in the main domain (Inverse Covariance matrix domain). In addition to the proposed algorithm, the convergence analysis is also provided. In the Numerical Experiments Section, we show that the proposed method outperforms state-of-the-art methods in terms of accuracy.

Non-intrusive load monitoring (NILM), also known as energy disaggregation, is a blind source separation problem where a household's aggregate electricity consumption is broken down into electricity usages of individual appliances. In this way, the cost and trouble of installing many measurement devices over numerous household appliances can be avoided, and only one device needs to be installed. The problem has been well-known since Hart's seminal paper in 1992, and recently significant performance improvements have been achieved by adopting deep networks. In this work, we focus on the idea that appliances have on/off states, and develop a deep network for further performance improvements. Specifically, we propose a subtask gated network that combines the main regression network with an on/off classification subtask network. Unlike typical multitask learning algorithms where multiple tasks simply share the network parameters to take advantage of the relevance among tasks, the subtask gated network multiply the main network's regression output with the subtask's classification probability. When standby-power is additionally learned, the proposed solution surpasses the state-of-the-art performance for most of the benchmark cases. The subtask gated network can be very effective for any problem that inherently has on/off states.

Huge numbers of people are suffering from "social jet lag" and might be accidentally disrupting their body clocks, according to new research. The problem could stop people getting enough sleep and disrupting their schedules, in turn leading to problems like obesity, diabetes and cardiovascular disease, according to researchers. The new study found that people across the US – and probably elsewhere – are suffering from the problem that afflicts their biological clock. Uber has halted testing of driverless vehicles after a woman was killed by one of their cars in Tempe, Arizona. The I.F.O. is fuelled by eight electric engines, which is able to push the flying object to an estimated top speed of about 120mph The giant human-like robot bears a striking resemblance to the military robots starring in the movie'Avatar' and is claimed as a world first by its creators from a South Korean robotic company Waseda University's saxophonist robot WAS-5, developed by professor Atsuo Takanishi and Kaptain Rock playing one string light saber guitar perform jam session A man looks at an exhibit entitled'Mimus' a giant industrial robot which has been reprogrammed to interact with humans during a photocall at the new Design Museum in South Kensington, London Electrification Guru Dr. Wolfgang Ziebart talks about the electric Jaguar I-PACE concept SUV before it was unveiled before the Los Angeles Auto Show in Los Angeles, California, U.S The Jaguar I-PACE Concept car is the start of a new era for Jaguar.

Japan's new cybersecurity minister has never used a computer and doesn't seem to know what a USB port is. The bizarre admission has prompted mockery in Japan and across the world, but newly appointed Yoshitaka Sakurada says that it is unlikely he will have to actually use a computer, despite being responsible for ensuring that the country's millions of devices are kept safe. Instead, cybersecurity policy is set by a large number of people and aides can type into the computer for him, he said. Mr Sakurada has been in parliament for 22 years but has not held such a senior position before, now finding himself responsible both for cybersecurity and the 2020 Tokyo Olympics. Uber has halted testing of driverless vehicles after a woman was killed by one of their cars in Tempe, Arizona.

Smartphone maker Huawei is planning on taking its popular voice assistant outside of China and competing with Amazon, Google and Apple internationally, according to a report from CNBC. The Chinese technology firm is apparently working on a version of its voice assistant Xiaoyi that will work outside of China, though it hasn't revealed what languages the AI will speak, nor when it will be available for other markets. Prior to developing Xiaoyi, Huawei was reliant on third-party voice assistants including Google Assistant and Amazon Alexa. The company's first smart speaker, the AI Cube, relied on Alexa. Huawei has been building on its own voice assistant in recent months. Its newest device, the AI Speaker, uses Xiaoyi, as does its latest line of smartphones.

Art appreciation is highly subjective. Fraiberger et al. used an extensive record of exhibition and auction data to study and model the career trajectory of individual artists relative to a network of galleries and museums. They observed a lock-in effect among highly reputed artists who started their career in high-prestige institutions and a long struggle for access to elite institutions among those who started their career at the network periphery. In areas of human activity where performance is difficult to quantify in an objective fashion, reputation and networks of influence play a key role in determining access to resources and rewards. To understand the role of these factors, we reconstructed the exhibition history of half a million artists, mapping out the coexhibition network that captures the movement of art between institutions.

Apple has won an international award in recognition of its attempts to stop slavery and the work it has done to rid it from its supply chain. The Stop Slavery Award, which the Thomson Reuters Foundation said was in recognition of a "giant leap in the fight against slavery", comes after a concerted effort by Apple to ensure it is more transparent about its supply chain. Apple says it has worked hard to combat the kinds of abuse that happen in suppliers used by a wide variety of companies, such as workers who are forced into modern slavery by having their passports taken away or being saddled with huge debts they must work to pay off. Uber has halted testing of driverless vehicles after a woman was killed by one of their cars in Tempe, Arizona. The I.F.O. is fuelled by eight electric engines, which is able to push the flying object to an estimated top speed of about 120mph The giant human-like robot bears a striking resemblance to the military robots starring in the movie'Avatar' and is claimed as a world first by its creators from a South Korean robotic company Waseda University's saxophonist robot WAS-5, developed by professor Atsuo Takanishi and Kaptain Rock playing one string light saber guitar perform jam session A man looks at an exhibit entitled'Mimus' a giant industrial robot which has been reprogrammed to interact with humans during a photocall at the new Design Museum in South Kensington, London Electrification Guru Dr. Wolfgang Ziebart talks about the electric Jaguar I-PACE concept SUV before it was unveiled before the Los Angeles Auto Show in Los Angeles, California, U.S The Jaguar I-PACE Concept car is the start of a new era for Jaguar.

Recently, analysts have argued that emerging technologies with military applications may undermine nuclear stability (see here, here, and here), but the logic of these arguments is debatable and overlooks a more straightforward reason why new technology might cause nuclear conflict: by upending the existing balance of power among nuclear-armed states. This latter concern is more probable and dangerous and demands an immediate policy response. For more than 70 years, the world has avoided major power conflict, and many attribute this era of peace to nuclear weapons. In situations of mutually assured destruction (MAD), neither side has an incentive to start a conflict because doing so will only result in its own annihilation. The key to this model of deterrence is the maintenance of secure second-strike capabilities--the ability to absorb an enemy nuclear attack and respond with a devastating counterattack.