We consider the setting of an agent with a fixed body interacting with an unknown and uncertain external world. We show that models trained to predict proprioceptive information about the agent's body come to represent objects in the external world. In spite of being trained with only internally available signals, these dynamic body models come to represent external objects through the necessity of predicting their effects on the agent's own body. That is, the model learns holistic persistent representations of objects in the world, even though the only training signals are body signals. Our dynamics model is able to successfully predict distributions over 132 sensor readings over 100 steps into the future and we demonstrate that even when the body is no longer in contact with an object, the latent variables of the dynamics model continue to represent its shape. We show that active data collection by maximizing the entropy of predictions about the body---touch sensors, proprioception and vestibular information---leads to learning of dynamic models that show superior performance when used for control. We also collect data from a real robotic hand and show that the same models can be used to answer questions about properties of objects in the real world. Videos with qualitative results of our models are available at https://goo.gl/mZuqAV.

Researchers have created a new metallic glass that is stronger and lighter than some of the best steel, while standing up to corrosion and wear. A team from the Department of Energy's SLAC National Accelerator Laboratory, the National Institute of Standards and Technology (NIST) and Northwestern University used a new system at SLAC's Stanford Synchrotron Radiation Lightsource (SSRL) that combines machine learning with experiments that quickly make and screen hundreds of sample materials at a time. This allowed the researchers to discover three new blends of ingredients that form metallic glass about 200 times faster than before. While there are millions of possible combinations of ingredients for metallic glass, only a few thousand combinations have been evaluated in the last 50 years, with only a select few being developed to the point where they can be commercially useful. "It typically takes a decade or two to get a material from discovery to commercial use," Chris Wolverton, the Jerome B. Cohen Professor of Materials Science and Engineering in Northwestern's McCormick School of Engineering, said in a statement.

While reading about tools and frameworks can give C-level decision-makers ideas for incorporating the technology, it's also worth exploring how others are making use of AI; after all, it's important to close gaps created by your AI-adopting competitors. Here are a few AI use cases executives need to explore. Dealing with fraud is all but inevitable when working in the financial sector. Retail stores assume some amount of theft as part of doing business. Classic monitoring is still essential for detecting fraud and theft, but AI systems can go a step further and detect problems while they're underway.

As France's youngest president at 40 years old, Emmanuel Macron is known for his strong handshake, boyish good looks, and his controversial method of selecting a mate. Recently, he set his sights on artificial intelligence, announcing a government program to invest $1.8 billion into AI over the next four years. The cornerstone of all this spending will be in the healthcare sector, where the aim is to make predictive and personalized care a reality using AI and big data. This prompted us to take a look at the ten most funded French AI startups according to Crunchbase. Founded in 2014, Shift Technology has raised $40 million to develop an AI-based insurance fraud detection service.

A coastal area in Fukushima Prefecture's Minamisoma, which seven years ago was overtaken by tsunami debris, is set to be resurrected as a major robotics research site. The Fukushima Robot Test Field, a 50-hectare site being built by the Fukushima Prefectural Government, is meant to be used by both domestic and foreign companies to develop robotics technologies. The site will be the central facility for the Innovation Coast project, the aim of which is to create new industries in tsunami-hit areas. But some of the participants are still waiting for the project to show signs of life. At the site, large fields for drone tests and a telecommunications tower are scheduled to be completed by June.

The home of the future looks an increasingly attractive place to live this week, after millions of households received the unwelcome news that their energy bills were going up again. Switching supplier is one quick fix to rising bills. But in the long run, industry players say the answers may lie in a coming revolution in how we use energy in our homes, turning them into mini power stations and reducing our reliance on energy companies such as British Gas and EDF. For consumers, cost and convenience will be big factors. For energy firms, there is a chance to rebuild trust and transform themselves from mere suppliers into more profitable service companies.

But once in a while, under just the right conditions, you get something entirely new: a futuristic alloy called metallic glass. The amorphous material's atoms are arranged every which way, much like the atoms of the glass in a window. Its glassy nature makes it stronger and lighter than today's best steel, and it stands up better to corrosion and wear. Although metallic glass shows a lot of promise as a protective coating and alternative to steel, only a few thousand of the millions of possible combinations of ingredients have been evaluated over the past 50 years, and only a handful developed to the point that they may become useful. Now a group led by scientists at the Department of Energy's SLAC National Accelerator Laboratory, the National Institute of Standards and Technology (NIST) and Northwestern University has reported a shortcut for discovering and improving metallic glass -- and, by extension, other elusive materials -- at a fraction of the time and cost.

Fault detection problem for closed loop uncertain dynamical systems, is investigated in this paper, using different deep learning based methods. Traditional classifier based method does not perform well, because of the inherent difficulty of detecting system level faults for closed loop dynamical system. Specifically, acting controller in any closed loop dynamical system, works to reduce the effect of system level faults. A novel Generative Adversarial based deep Autoencoder is designed to classify datasets under normal and faulty operating conditions. This proposed network performs significantly well when compared to any available classifier based methods, and moreover, does not require labeled fault incorporated datasets for training purpose. Finally, this aforementioned network's performance is tested on a high complexity building energy system dataset.

In internet era, users grant Internet companies permission on collecting their personal data for connecting with creditable users and content out of convenience. For example, the magazine publishes articles on Facebook because Facebook allows users to subscribe their article. At the same time, the publisher can manage their subscribers' relationship with messenger system. The recommendation system helped to rank users and their content published. All the free services are sponsored from advertisements, which pay the cost of internet space and traffic.

In internet era, users grant Internet companies permission on collecting their personal data for connecting with creditable users and content out of convenience. For example, the magazine publishes articles on Facebook because Facebook allows users to subscribe their article. At the same time, the publisher can manage their subscribers' relationship with messenger system. The recommendation system helped to rank users and their content published. All the free services are sponsored from advertisements, which pay the cost of internet space and traffic.