Approximate variational inference has shown to be a powerful tool for modeling unknown complex probability distributions. Recent advances in the field allow us to learn probabilistic models of sequences that actively exploit spatial and temporal structure. We apply a Stochastic Recurrent Network (STORN) to learn robot time series data. Our evaluation demonstrates that we can robustly detect anomalies both off- and on-line.

Resolving a conjecture of Abbe, Bandeira and Hall, the authors have recently shown that the semidefinite programming (SDP) relaxation of the maximum likelihood estimator achieves the sharp threshold for exactly recovering the community structure under the binary stochastic block model of two equal-sized clusters. The same was shown for the case of a single cluster and outliers. Extending the proof techniques, in this paper it is shown that SDP relaxations also achieve the sharp recovery threshold in the following cases: (1) Binary stochastic block model with two clusters of sizes proportional to network size but not necessarily equal; (2) Stochastic block model with a fixed number of equal-sized clusters; (3) Binary censored block model with the background graph being Erd\H{o}s-R\'enyi. Furthermore, a sufficient condition is given for an SDP procedure to achieve exact recovery for the general case of a fixed number of clusters plus outliers. These results demonstrate the versatility of SDP relaxation as a simple, general purpose, computationally feasible methodology for community detection.

HE need to study and analyze complex systems arises in many fields. Nowadays, in more and more applications and devices, many sensors are used to collect and to record multiple channels of data, a fact that increases the amount of information available to analyze the state of the system of interest. In such cases, it is typically insufficient to study each channel separately. Yet, the ability to gain a deep understanding of the true state of the system from the overwhelming amount of collected data from multiple (usually different) sources of information is challenging; it calls for the development of new technologies and novel ways to observe the system of interest and to fuse the available information [1]. For example, the study of human physiology in many fields of medicine is performed by simultaneously monitoring various medical features through electroencephalography (EEG) signals, electrocardiography (ECG) signals, respiratory signals, etc. Each type of measurement carries different and specific information, while our purpose is to systematically discover an accurate description of the state of the patient/person. A commonly-used method that has the ability to reveal correlations between multiple different sets, which often furthers our understanding of the system, is the Canonical Correlation Analysis (CCA) [2]-[4]. CCA is a well known and studied algorithm, where linear projections maximizing the correlation between the two data sets are constructed.

Probabilistic inference over large data sets is a challenging data management problem since exact inference is generally #P-hard and is most often solved approximately with sampling-based methods today. This paper proposes an alternative approach for approximate evaluation of conjunctive queries with standard relational databases: In our approach, every query is evaluated entirely in the database engine by evaluating a fixed number of query plans, each providing an upper bound on the true probability, then taking their minimum. We provide an algorithm that takes into account important schema information to enumerate only the minimal necessary plans among all possible plans. Importantly, this algorithm is a strict generalization of all known PTIME self-join-free conjunctive queries: A query is in PTIME if and only if our algorithm returns one single plan. Furthermore, our approach is a generalization of a family of efficient ranking methods from graphs to hypergraphs. We also adapt three relational query optimization techniques to evaluate all necessary plans very fast. We give a detailed experimental evaluation of our approach and, in the process, provide a new way of thinking about the value of probabilistic methods over non-probabilistic methods for ranking query answers. We also note that the techniques developed in this paper apply immediately to lifted inference from statistical relational models since lifted inference corresponds to PTIME plans in probabilistic databases.

Apple, like practically every mega-corporation, wants to know as much as possible about its customers. But it's also marketed itself as Silicon Valley's privacy champion, one that--unlike so many of its advertising-driven competitors--wants to know as little as possible about you. So perhaps it's no surprise that the company has now publicly boasted about its work in an obscure branch of mathematics that deals with exactly that paradox. At the keynote address of Apple's Worldwide Developers' Conference in San Francisco on Monday, the company's senior vice president of software engineering Craig Federighi gave a his familiar nod to privacy, emphasizing that Apple doesn't assemble user profiles, does end-to-end encrypt iMessage and Facetime and tries to keep as much computation as possible that involves your private information on your personal device rather than on an Apple server. But Federighi also acknowledged the growing reality that collecting user information is crucial to making good software, especially in an age of big data analysis and machine learning.

Virtual personal assistants can do just about everything: They can help a person order things online, turn the lights on and off, or play music from a favorite playlist. A new personal assistant is joining the abundance of time-management tools out there, using artificial intelligence to help developers tackle the problems of managing their time and scheduling everything so their day can be fulfilling. The virtual assistant's name is Trevor AI, and it's an app that is available today in the App Store. Development for Android will begin as soon as the app secures funding, which should happen in the next two months. The project for Trevor AI started when founder George Petrov, a business and computer software expert, brought his raw idea to the Founder Institute in Sofia, Bulgaria in December 2015.

Artificial technology is the future of the world. Why not position yourself with one of the most lucrative industries of the next 50 years: biotech! IBIS World says about biotechnology: "The industry is expected to continue prospering over the next five years, with the Asia-Pacific region making significant investments to gain a foothold in the market..." According to Wikipedia: "Biotechnology is the use of living systems and organisms to develop or make products, or "any technological application that uses biological systems, living organisms or derivatives thereof, to make or modify products or processes for specific use" (UN Convention on Biological Diversity, Art. 2). Depending on the tools and applications, it often overlaps with the (related) fields of bioengineering, biomedical engineering, biomanufacturing, etc." Biotech-now.org But in reality, health care outpaced the tech sector in 2014 by generating over 28 billion in economic activity and employing over 20% of San Francisco workers."

At the annual //build conference a few months ago Microsoft launched its bot platform. Bots built using our development tools and AI services enable natural language interaction with hundreds of millions of users across Skype and other services, and do everything from telling jokes to answering questions to booking travel. Since then, there have been thousands of conversations with bots over Skype, as well as a huge amount of interest from bot developers building all kinds of fun, interactive and intelligent bots. We're inviting you to come and build an awesome bot at Skype Palo Alto on June 21-22, with the help of the Microsoft bot team and AI experts from Cortana, Bing and Microsoft Research. We'll have sessions on bot best practices, early access to our latest development tools, great food to keep you going and plenty of swag.

The tech giant kicked off its annual software conference by announcing new software features for the Apple Watch and Apple TV, as well, while unveiling a new design for the Apple Music service. It's also extending Apple Pay to the web, so users can pay for purchases made on their Mac computers. Most of these new features won't arrive until this fall. At a time when sales of its flagship iPhone are slowing, Apple seemed determined to show that it can make its gadgets indispensable, or at least as useful as its competitors' products. Still, the tech giant is taking a cautious approach to integrating computer intelligence into its online services.

Apple's sweeping new artificial intelligence play takes a page from features introduced by rival tech companies in recent years -- but adds the polished, user-friendly twist that consumers have come to expect from the electronics giant. At the company's annual developer's conference in San Francisco on Monday, Apple executives announced a raft of features in the company's soon-to-be released desktop and mobile operating systems that are powered by artificial intelligence, or the blend of powerful computing capabilities and software algorithms. Such technology can make the phone or other device appear smarter because it anticipates the types of activities people want to do. Apple also said it was opening up many applications to outside developers, including its messaging platform iMessage, Maps and virtual assistant Siri, a departure for the company, which in the past has kept these systems tightly controlled. For Apple, more AI and more integrations with third party services will mean less fatigue for consumers, who are already overwhelmed with too many apps, too many devices, and too much data.