H2O is Google-scale open source machine learning engine for R & Big Data. This live webinar introduces Distributed Deep Learning concepts, implementation and results from recent developments. Real world classification & regression use cases from eBay text dataset, MNIST handwritten digits and Cancer datasets will present the power of this game changing technology.

Nasa has announced that it has found evidence of flowing water on Mars. Scientists have long speculated that Recurring Slope Lineae -- or dark patches -- on Mars were made up of briny water but the new findings prove that those patches are caused by liquid water, which it has established by finding hydrated salts. Several hundred camped outside the London store in Covent Garden. The 6s will have new features like a vastly improved camera and a pressure-sensitive "3D Touch" display

If Gabe Otte '11 hadn't had a Cornell advisor who steered him down a more challenging path and hadn't had some chance conversations with Nobel Prize-winning chemist Roald Hoffman, he might be squirreled away in a lab somewhere. Instead, he's the CEO of Freenome, a start-up just awarded 5.5 million in venture capital for its product, a data-driven blood test that can detect various types of cancers in their earliest stages and recommend the best treatments. Otte came to Cornell planning to study computer science, but a freshman-year advisor encouraged him to choose another major. "I had been coding and programming since I was nine years old," Otte said, so he elected to study chemistry and computational biology, using his knack for computer science to do his homework. "I fell in love with chemistry when I took organic chemistry," he said, adding that he developed his own computer program to do computations related to the synthesis of molecules.

Precision medicine [1] has become a most promising methodology for clinical medicine, which relies heavily on rich biomedical knowledge and information of individual patients such as genetic content, living habits, environmental factors, etc. [2]. US National Academy of Sciences claims in a 2011 research report that a biomedical knowledge network based on biological data and knowledge is necessary for precision medicine [3]. How to compute relatedness between concepts and discover valuable information and implicit knowledge effectively and efficiently from such hybrid knowledge (both structural and non-structural) networks is a key of paramount importance to the realization of precision medicine, and a huge challenge facing the biomedical research community. It is agreeable that the knowledge network should include all the knowledge sources, information systems and repositories in biomedicine available today and in the future, spanning the whole spectrum of structural and non-structural information and knowledge. One type of important knowledge sources is ontology.

Samsonovich made the comments while attending the 2016 Annual International Conference on Biologically Inspired Cognitive Architectures (BICA) in New York City, which takes place from July 16-19. The conference was sponsored by MEPhl and attracted more than 200 participants. "We are on the verge of a major breakthrough that was discussed since the fifties of the previous century," Samsonovich said on Tuesday. The breakthrough, according to Samsonovich, is the creation of free thinking machines capable of feeling and understanding human emotions, understanding narratives and thinking in those narratives, as well as being capable to actively learn on their own. "Those are the three key capabilities in my view that will determine the breakthrough," Samsonovich said, adding that progress is expected to be made in "several years."

The empirically successful Thompson Sampling algorithm for stochastic bandits has drawn much interest in understanding its theoretical properties. One important benefit of the algorithm is that it allows domain knowledge to be conveniently encoded as a prior distribution to balance exploration and exploitation more effectively. While it is generally believed that the algorithm's regret is low (high) when the prior is good (bad), little is known about the exact dependence. In this paper, we fully characterize the algorithm's worst-case dependence of regret on the choice of prior, focusing on a special yet representative case. These results also provide insights into the general sensitivity of the algorithm to the choice of priors. In particular, with $p$ being the prior probability mass of the true reward-generating model, we prove $O(\sqrt{T/p})$ and $O(\sqrt{(1-p)T})$ regret upper bounds for the bad- and good-prior cases, respectively, as well as \emph{matching} lower bounds. Our proofs rely on the discovery of a fundamental property of Thompson Sampling and make heavy use of martingale theory, both of which appear novel in the literature, to the best of our knowledge.

The problem of machine emotional intelligence is very broad and multifaceted; one of its challenges being the very fact that is hard to define it in an unambiguous way. There is no unique definition of emotion, and there is neither a specific method nor a particular required dataset that is guaranteed to capture it. One of the most popular emotion definitions is the one of the six basic emotions by Paul Ekman [1]. The original six emotions he proposed are: anger, disgust, fear, happiness, sadness and surprise. Another very popular approach is the 2-dimensional emotion map, where each emotional state is projected on the orthogonal axes of valence and arousal [2]. A third dimension can be added to this space with the axis of dominance, see [3] and its related references.

We show how to train a quantum network of pairwise interacting qubits such that its evolution implements a target quantum algorithm into a given network subset. Our strategy is inspired by supervised learning and is designed to help the physical construction of a quantum computer which operates with minimal external classical control.

We propose a method that performs anomaly detection and localisation within heterogeneous data using a pairwise undirected mixed graphical model. The data are a mixture of categorical and quantitative variables, and the model is learned over a dataset that is supposed not to contain any anomaly. We then use the model over temporal data, potentially a data stream, using a version of the two-sided CUSUM algorithm. The proposed decision statistic is based on a conditional likelihood ratio computed for each variable given the others. Our results show that this function allows to detect anomalies variable by variable, and thus to localise the variables involved in the anomalies more precisely than univariate methods based on simple marginals.

Deep learning has gained great popularity due to its widespread success on many inference problems. We consider the application of deep learning to the sparse linear inverse problem encountered in compressive sensing, where one seeks to recover a sparse signal from a small number of noisy linear measurements. In this paper, we propose a novel neural-network architecture that decouples prediction errors across layers in the same way that the approximate message passing (AMP) algorithm decouples them across iterations: through Onsager correction. Numerical experiments suggest that our "learned AMP" network significantly improves upon Gregor and LeCun's "learned ISTA" network in both accuracy and complexity.