By rights, Yuval Noah Harari should be an anonymous academic buried in an obscure university department somewhere toiling away on his somewhat dusty discipline – medieval military history. He's a professor of history at the Hebrew University of Jerusalem and there is almost nothing in his background to suggest that he would write a book that has become one of the most talked about non-fiction bestsellers of the year – Sapiens. Or that he'd join the globetrotting TED-ocracy: the academic superstars who travel the world delivering keynotes on zeitgeisty topics, in Harari's case, the not inconsiderable subject of the history of the whole of mankind. When I meet him, he's just been the star turn at Penguin Random House's global sales conference. In May, he packed out Hay. Earlier this month, he delivered a TED talk.

Graduates of a Southern California high school received a head-scratching surprise on their diploma covers Thursday. Students of the Ontario High School class of 2016 received their diploma covers with an egregious spelling error on the front. Photos on social media showed the cover was spelled as "Ontario High Shcool." A Chaffey Joint Union High School District official told KTLA Friday that a "printing error" was to blame for the typo that was on the covers. "The misspelling was a printing error made by the grad products company," Chaffey Joint Union High School District Superintendent Mathew Holton said in a statement to KTLA.

Deep conditional generative models are developed to simultaneously learn the temporal dependencies of multiple sequences. The model is designed by introducing a three-way weight tensor to capture the multiplicative interactions between side information and sequences. The proposed model builds on the Temporal Sigmoid Belief Network (TSBN), a sequential stack of Sigmoid Belief Networks (SBNs). The transition matrices are further factored to reduce the number of parameters and improve generalization. When side information is not available, a general framework for semi-supervised learning based on the proposed model is constituted, allowing robust sequence classification. Experimental results show that the proposed approach achieves state-of-the-art predictive and classification performance on sequential data, and has the capacity to synthesize sequences, with controlled style transitioning and blending.

With the enormous growth of data size n and model complexity, asynchronous parallel algorithms [1, 2, 3, 4, 5, 6] have become an important tool and received significant successes for solving large scale machine learning problems in the form of (1). Asynchronous parallel algorithms distribute computation on multicore systems (shared memory architecture) or multi-machine system (parameter server architecture), whose computation power generally scales up with the increasing number of cores or machines. As a consequence, effective design and implementation of asynchronous parallel algorithms is critical for large scale machine learning. Numerous efforts have been devoted to this topic. Among them, asynchronous stochastic gradient descent is proposed in [1, 2], and its performance is guaranteed by theoretical convergence analyses. An asynchronous proximal gradient descent algorithm is designed on the parameter server architecture in [3] with a distributed optimization software provided. Convergence rate of asynchronous stochastic gradient descent with a nonconvex objective is analyzed in [4].

Formal synthesis is the process of generating a program satisfying a high-level formal specification. In recent times, effective formal synthesis methods have been proposed based on the use of inductive learning. We refer to this class of methods that learn programs from examples as formal inductive synthesis. In this paper, we present a theoretical framework for formal inductive synthesis. We discuss how formal inductive synthesis differs from traditional machine learning. We then describe oracle-guided inductive synthesis (OGIS), a framework that captures a family of synthesizers that operate by iteratively querying an oracle. An instance of OGIS that has had much practical impact is counterexample-guided inductive synthesis (CEGIS). We present a theoretical characterization of CEGIS for learning any program that computes a recursive language. In particular, we analyze the relative power of CEGIS variants where the types of counterexamples generated by the oracle varies. We also consider the impact of bounded versus unbounded memory available to the learning algorithm. In the special case where the universe of candidate programs is finite, we relate the speed of convergence to the notion of teaching dimension studied in machine learning theory. Altogether, the results of the paper take a first step towards a theoretical foundation for the emerging field of formal inductive synthesis.

Software engineering is about developing programs or tools to automate tasks. Instead of "doing things manually," we write programs; a program is basically just a machine-readable set of instructions that can be executed by a computer. Let's consider a classic example: e-mail spam filtering. Assuming that we have access to the source code of our e-mail client and know how to handle it, we could come up with an instinctive set of rules that may help us with our spam problem. For example: if not "sender in contacts": if "subject line contains BUY!: e-mail spam folder:" else if ... It is intuitive to say that coming up with these rules is a pretty tedious task.

A few weekends ago, on a snowy Saturday in April (not uncommon in Denver), I signed into Kaggle for the first time in several months, looking to play around with some competition data in order to while away the chilly day. My kids' endless chatter and my wife's disapproving looks faded into the background, and I blissfully wrangled data from the Expedia Hotel Recommendation competition for several hours. I submitted a few entries, slowly climbing the leaderboard until I got to the top 1/3 of scores, and then finally I got up to help with my family duties. That night in bed, my mind whirled with possibilities for what I could do with the data to improve my score – different variables I could use, several time-related features I could engineer, and thoughts about how to ensemble a couple dissimilar models together. I woke up early Sunday and fired up my project in RStudio.

In this paper, we study the problem of online optimization of piecewise constant functions. This is motivated by the question of selecting optimal parameters for learning algorithms. Recently, Gupta and Roughgarden (2016) introduced a probably approximately correct (PAC) framework for choosing parameters of algorithms. Imagine a situation, when a website wishes to provide personalized results to a user. To respond to a user's query, the service provider may need to implement a learning (or some other type of) algorithm which involves choosing parameters. The choice of parameters affects the quality of solution and ideally we would like to design a mechanism where the service provider learns from past instances, or at least employs a strategy that has low regret with respect to the single optimal solution in hindsight. In many learning problems, the goal is to find parameters by optimizing a continuous function (of the parameters); however, ever so often one encounters problems with discrete solutions, such as k-means or independent set, which result in objective functions that have discontinuities. Concretely, we consider the problem of online optimization of piecewise constant functions over the domain [0, 1).

College of Computing Professor Ashok Goel teaches Knowledge Based Artificial Intelligence (KBAI) every semester. And every time he offers it, Goel estimates, his 300 or so students post roughly 10,000 messages in the online forums -- far too many inquiries for him and his eight teaching assistants (TA) to handle. That's why Goel added a ninth TA this semester. Her name is Jill Watson, and she's unlike any other TA in the world. Jill is a computer -- a virtual TA -- implemented, in part, using technologies from IBM's Watson platform.

WIRE)--TSYS (NYSE: TSS), today announced an agreement with Featurespace, a global leader in adaptive behavioral analytics, that will reduce fraud for its clients with a revolutionary machine learning software platform -- the ARICSM engine -- that monitors every individual -- one customer at a time -- to deliver real-time decision capabilities. "We are proud to be working with TSYS to deliver world-leading machine learning fraud protection and exceptional customer management to their clients." Featurespace is the world-leader in Adaptive Behavioural Analytics and creator of the ARICSM engine, a machine learning software platform which understands individual behaviours in real-time for decision making around fraud, risk and compliance. We provide the ARIC Fraud Hub to organisations in banking, payments, and gaming to spot new fraud attacks as they occur, reduce customer friction by reducing false fraud alerts, and improve operational efficiencies in managing fraud, risk and compliance.