Thisabstract extends on the previous work [21, 22] on program induction[16] using probabilistic programming. It describes possible further steps to extend that work, such that, ultimately, automatic probabilistic program synthesis can generalise over any reasonable set of inputs and outputs, in particular in regard to text, image and video data.

We address the problem of phase retrieval (PR) from quantized measurements. The goal is to reconstruct a signal from quadratic measurements encoded with a finite precision, which is indeed the case in many practical applications. We develop a rank-1 projection algorithm that recovers the signal subject to ensuring consistency with the measurement, that is, the recovered signal when encoded must yield the same set of measurements that one started with. The rank-1 projection stems from the idea of lifting, originally proposed in the context of PhaseLift. The consistency criterion is enforced using a one-sided quadratic cost. We also determine the probability with which different vectors lead to the same set of quantized measurements, which makes it impossible to resolve them. Naturally, this probability depends on how correlated such vectors are, and how coarsely/finely the measurements get quantized. The proposed algorithm is also capable of incorporating a sparsity constraint on the signal. An analysis of the cost function reveals that it is bounded, both above and below, by functions that are dependent on how well correlated the estimate is with the ground truth. We also derive the Cram\'er-Rao lower bound (CRB) on the achievable reconstruction accuracy. A comparison with the state-of-the- art algorithms shows that the proposed algorithm has a higher reconstruction accuracy and is about 2 to 3 dB away from the CRB. The edge, in terms of the reconstruction signal-to-noise ratio, over the competing algorithms is higher (about 5 to 6 dB) when the quantization is coarse.

Debates about rights are frequently framed around the concept of legal personhood, which is granted not just to human beings but also to some nonhuman entities, such as firms, corporations or governments. Legal entities, aka legal persons are granted certain privileges and responsibilities by the jurisdictions in which they are recognized, and many such rights are not available to nonperson agents. Attempting to secure legal personhood is often seen as a potential pathway to get certain rights and protections for animals [1], fetuses [2], trees, rivers [3] and artificially intelligent (AI) agents [4]. It is commonly believed that a court ruling or a legislative action is necessary to grant personhood to a new type of entity, but recent legal literature [5-8] suggests that loopholes in the current law may permit granting of legal personhood to currently existing AI/software without having to change the law or persuade any court.

Many optimization problems admit a number of local optima, among which there is the global optimum. For these problems, various heuristic optimization methods have been proposed. Comparing the results of these solvers requires the definition of suitable metrics. In the electrical energy systems literature, simple metrics such as best value obtained, the mean value, the median or the standard deviation of the solutions are still used. However, the comparisons carried out with these metrics are rather weak, and on these bases a somehow uncontrolled proliferation of heuristic solvers is taking place. This paper addresses the overall issue of understanding the reasons of this proliferation, showing that the assessment of the best solver can be cast into a perpetual motion scheme. Moreover, this paper shows how the use of more refined metrics defined to compare the optimization result, associated with the definition of appropriate benchmarks, may make the comparisons among the solvers more robust. The proposed metrics are based on the concept of first-order stochastic dominance and are defined for the cases in which: : (i) the globally optimal solution can be found (for testing purposes); and (ii) the number of possible solutions is so large that practically it cannot be guaranteed that the global optimum has been found. Illustrative examples are provided for a typical problem in the electrical energy systems area - distribution network reconfiguration. The conceptual results obtained are generally valid to compare the results of other optimization problems.

ETH Zurich is developing a robot dog that seems to be much friendlier than the Boston Dynamics one. It can genuinely cooperate with humans to perform tasks such as moving heavy stuff, and it will even clean up after them. Subscribe for more tech & culture videos: http://on.mash.to/subscribe

NEW YORK: Communicators are bullish about artificial intelligence's potential to make their profession more efficient, according to a survey by MSLGroup and Publicis.Sapient. The study, Powered by AI: Communications in the Algorithm Age, surveyed more than 1,846 marketing and communications in-house leaders in Brazil, China, France, Germany, India, Italy, Poland, the U.K., and the U.S. MSL's parent, Publicis Groupe, is rolling out an AI platform called Marcel, which will essentially help its employees better collaborate and form teams more efficiently. MSL CEO Guillaume Herbette said he expects Marcel to be 100% operational by the end of the year. "AI will help us and our clients do better work," Herbette said. "It will add to brand-consumer engagement. They will try more than ever at [maintaining] that relationship."

While it might be tempting to dismiss Microsoft's AI technology hype as slick marketing to drum up sales revenue, a number of the company's customers said artificial intelligence is moving deeper into the real world. Several Microsoft blue-chip customers displayed their experiences with the company's customer experience AI technology here at the Microsoft Ignite 2018 conference. BMW uses AI and Azure's bot framework to enhance on-road driver support in cars. Swedish clothing retailer H&M launched Afound, an off-price outlet that includes physical stores in Sweden and globally via a digital marketplace infused with customer experience AI to drive sales. Two other retail giants, Nordstrom and Walmart, are remaking their online shopping experiences to match their online-only competitors.

At ROSCon 2018 in Madrid this weekend, Microsoft showed up with a small booth and a TurtleBot 3. The TurtleBot wasn't doing much, just sitting on a table, but it was sitting on the table while running ROS Melodic Morenia on Windows 10. Were it released onto the floor, it would have used its lidar to locate people and drive towards them, as a proof of concept that Microsoft has successfully gotten ROS to work in Windows. This isn't just an isolated demo, either. In a blog post, Lou Amadio (Windows IoT principal software engineer at Microsoft), says that "Microsoft is working with Open Robotics and the ROS Industrial Consortium to bring the Robot Operating System to Windows." One of the biggest obstacles to getting started with ROS is that it also involves getting started with Linux.

It's been two years since Salesforce formally introduced the Einstein AI platform that is supposed to help users find hidden insights within their data. At Dreamforce 18, some customers described how they have integrated Einstein AI capabilities into their business processes. Every Salesforce product has received some kind of Einstein AI upgrade, with more features rolled out with each product release. Companies like tire provider Michelin and Dublin-based recruiting company CPL are among the Salesforce customers that have found ways to use Einstein AI to help with productivity and revenue growth. "AI is there to enhance the human input," said Danielle DeLozier, global product owner for Service Cloud at Michelin, based in Clermont-Ferrand, France.

The trouble with the word artificial intelligence is the word intelligence. It misleads -- people conjure up images of thinking machines, Stephen Spielberg; Arnold Schwarzenegger coming back from the future and saying: "I'll be back." Who knows what the future may bring, but for now, and for all intents and purposes, people may be confusing intelligence and sentience. Neither are well defined -- we are supposedly sentient, machines are not, and for all we know, may never be. Intelligence means "the ability to acquire and apply knowledge and skills". These days machines can do that, machines learn, they deep learn, they can even learn by applying neural networks -- that does not make them like people, maybe they possess one subset, of a myriad of sets, that make us who we are.