In this paper we consider the problems of supervised classification and regression in the case where attributes and labels are functions: a data is represented by a set of functions, and the label is also a function. We focus on the use of reproducing kernel Hilbert space theory to learn from such functional data. Basic concepts and properties of kernel-based learning are extended to include the estimation of function-valued functions. In this setting, the representer theorem is restated, a set of rigorously defined infinite-dimensional operator-valued kernels that can be valuably applied when the data are functions is described, and a learning algorithm for nonlinear functional data analysis is introduced. The methodology is illustrated through speech and audio signal processing experiments.

We consider the problem of learning models for forecasting multiple time-series systems together with discovering the leading indicators that serve as good predictors for the system. We model the systems by linear vector autoregressive models (VAR) and link the discovery of leading indicators to inferring sparse graphs of Granger-causality. We propose new problem formulations and develop two new methods to learn such models, gradually increasing the complexity of assumptions and approaches. While the first method assumes common structures across the whole system, our second method uncovers model clusters based on the Granger-causality and leading indicators together with learning the model parameters. We study the performance of our methods on a comprehensive set of experiments and confirm their efficacy and their advantages over state-of-the-art sparse VAR and graphical Granger learning methods.

Sparse coding, which represents a data point as a sparse reconstruction code with regard to a dictionary, has been a popular data representation method. Meanwhile, in database retrieval problems, learning the ranking scores from data points plays an important role. Up to now, these two problems have always been considered separately, assuming that data coding and ranking are two independent and irrelevant problems. However, is there any internal relationship between sparse coding and ranking score learning? If yes, how to explore and make use of this internal relationship? In this paper, we try to answer these questions by developing the first joint sparse coding and ranking score learning algorithm. To explore the local distribution in the sparse code space, and also to bridge coding and ranking problems, we assume that in the neighborhood of each data point, the ranking scores can be approximated from the corresponding sparse codes by a local linear function. By considering the local approximation error of ranking scores, the reconstruction error and sparsity of sparse coding, and the query information provided by the user, we construct a unified objective function for learning of sparse codes, the dictionary and ranking scores. We further develop an iterative algorithm to solve this optimization problem.

Inference methods are often formulated as variational approximations: these approximations allow easy evaluation of statistics by marginalization or linear response, but these estimates can be inconsistent. We show that by introducing constraints on covariance, one can ensure consistency of linear response with the variational parameters, and in so doing inference of marginal probability distributions is improved. For the Bethe approximation and its generalizations, improvements are achieved with simple choices of the constraints. The approximations are presented as variational frameworks; iterative procedures related to message passing are provided for finding the minima.

Recent progress in artificial intelligence (AI) has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats humans in some respects. Despite their biological inspiration and performance achievements, these systems differ from human intelligence in crucial ways. We review progress in cognitive science suggesting that truly human-like learning and thinking machines will have to reach beyond current engineering trends in both what they learn, and how they learn it. Specifically, we argue that these machines should (a) build causal models of the world that support explanation and understanding, rather than merely solving pattern recognition problems; (b) ground learning in intuitive theories of physics and psychology, to support and enrich the knowledge that is learned; and (c) harness compositionality and learning-to-learn to rapidly acquire and generalize knowledge to new tasks and situations. We suggest concrete challenges and promising routes towards these goals that can combine the strengths of recent neural network advances with more structured cognitive models.

Even if self-driving cars aren't part of our daily lives yet, vehicles are becoming internet-connected at a rapid pace. Gartner predicts that one fifth of all autos on the road, and great majority of new vehicles being produced worldwide will have wireless network connectivity by 2020. Yet, few organizations have access to use the data generated by these vehicles today. That's where Otonomo, a startup based in Herzliya, Israel comes in. The company's systems gather up driver and vehicle data from disparate automakers and original equipment manufacturers.

DB: Imagine what the next 5 years will bring: The term "mobile computing" will eventually become a dated term, replaced by "ubiquitous computing" as the internet will be everywhere. These changes include the transportation we take on land, in the air, and at sea; the clothes and devices we wear, sensors at work, at home, in our environment, and (if we chose) in us for medical purposes as well. DB: Also right behind and coupled with the Internet of Everything: 3D mass fabricators enabling individuals to affordably "print" and modify at the molecular level tangible substances based on digital designs. Maker Faires around the world already exist showcasing the early stages of what 3D fabricators can do in the hands of artists, engineers, and hobbyists. As Co-Chair of the IEEE Committee focused on Artificial Intelligence and Innovative Policies, I firmly believe exponential changes like the era we're in offer great opportunities for society -- as well as great challenges.

The alliance is the latest by IBM in a bid to harness Watson's cognitive learning capabilities to benefit millions of college students and professors. The announcement follows a separate agreement announced at the end of June between IBM and Blackboard, and the roll out of an IBM Watson-enabled app for Apple earlier this month, among other initiatives. For Pearson, the alliance represents a chance to combine its global offering of digital learning products with IBM's cognitive learning platform in an effort to give students a more immersive learning experience with their college courses. And it promises to give instructors greater insights about how well students are navigating through their courses. To accomplish that, Watson will essentially ingest and analyze all of Pearson courseware.

An artificial intelligence (AI) judge has accurately predicted most verdicts of the European Court of Human Rights, and might soon be making important decisions about cases. Scientists built an artificial intelligence computer that was able to look at legal evidence as well as considering ethical questions to decide how a case should be decided. And it predicted those with 79 per cent accuracy, according to its creators. The algorithm looked at data sets made up 584 cases relating to torture and degrading treatment, fair trials and privacy. The computer was able to look through that information and make its own decision – which lined up with those made by Europe's most senior judges in almost every case.

A tutorial given by Chris Dyer, Yoav Goldberg, and Graham Neubig at EMNLP 2016 in Austin. The tutorial covers the basic of neural networks for NLP, and how to implement a variety of networks simply and efficiently in the DyNet toolkit.