Binary classification is one of the most common problem in machine learning. It consists in predicting whether a given element is of a particular class. In this paper, a new algorithm for binary classification is proposed using a hypergraph representation. Each element to be classified is partitioned according to its interactions with the training set. For each class, the total support is calculated as a convex combination of the {\it evidence} strength of the element of the partition. The evidence measure is pre-computed using the hypergraph induced by the training set and iteratively adjusted through a training phase. It does not require structured information, each case being represented by a set of {\it agnostic information} atoms. Empirical validation demonstrates its high potential on a wide range of well-known datasets and the results are compared to the state-of-art. The time complexity is given and empirically validated. Its capacity to provide good performances without hyperparameter tuning compared to standard classification methods is studied. Finally, the limitation of the model space is discussed and some potential solutions proposed.

Appropriate treatment regimens play a vital role in improving patient health status. Although some achievements have been made, few of the recent studies of learning treatment regimens have exploited different kinds of patient information due to the difficulty in adopting heterogeneous data to many data mining methods. Moreover, current studies seem too rigid with fixed intervals of treatment periods corresponding to the varying lengths of hospital stay. To this end, this work proposes a generic data-driven framework which can derive group-treatment regimens from electronic medical records by utilizing a mixed-variate restricted Boltzmann machine and incorporating medical domain knowledge. We conducted experiments on coronary artery disease as a case study. The obtained results show that the framework is promising and capable of assisting physicians in making clinical decisions.

We propose a deformable generator model to disentangle the appearance and geometric information from images into two independent latent vectors. The appearance generator produces the appearance information, including color, illumination, identity or category, of an image. The geometric generator produces displacement of the coordinates of each pixel and performs geometric warping, such as stretching and rotation, on the appearance generator to obtain the final synthesized image. The proposed model can learn both representations from image data in an unsupervised manner. The learned geometric generator can be conveniently transferred to the other image datasets to facilitate downstream AI tasks.

A longstanding goal in character animation is to combine data-driven specification of behavior with a system that can execute a similar behavior in a physical simulation, thus enabling realistic responses to perturbations and environmental variation. We show that well-known reinforcement learning (RL) methods can be adapted to learn robust control policies capable of imitating a broad range of example motion clips, while also learning complex recoveries, adapting to changes in morphology, and accomplishing user-specified goals. Our method handles keyframed motions, highly-dynamic actions such as motion-captured flips and spins, and retargeted motions. By combining a motion-imitation objective with a task objective, we can train characters that react intelligently in interactive settings, e.g., by walking in a desired direction or throwing a ball at a user-specified target. This approach thus combines the convenience and motion quality of using motion clips to define the desired style and appearance, with the flexibility and generality afforded by RL methods and physics-based animation. We further explore a number of methods for integrating multiple clips into the learning process to develop multi-skilled agents capable of performing a rich repertoire of diverse skills. We demonstrate results using multiple characters (human, Atlas robot, bipedal dinosaur, dragon) and a large variety of skills, including locomotion, acrobatics, and martial arts.

There is no free lunch, no single learning algorithm that will outperform other algorithms on all data. In practice different approaches are tried and the best algorithm selected. An alternative solution is to build new algorithms on demand by creating a framework that accommodates many algorithms. The best combination of parameters and procedures is searched here in the space of all possible models belonging to the framework of Similarity-Based Methods (SBMs). Such meta-learning approach gives a chance to find the best method in all cases. Issues related to the meta-learning and first tests of this approach are presented.

In this paper, we present an embedding-based framework (TrQuery) for recommending solutions of a SPARQL query, including approximate solutions when exact querying solutions are not available due to incompleteness or inconsistencies of real-world RDF data. Within this framework, embedding is applied to score solutions together with edit distance so that we could obtain more fine-grained recommendations than those recommendations via edit distance. For instance, graphs of two querying solutions with a similar structure can be distinguished in our proposed framework while the edit distance depending on structural difference becomes unable. To this end, we propose a novel score model built on vector space generated in embedding system to compute the similarity between an approximate subgraph matching and a whole graph matching. Finally, we evaluate our approach on large RDF datasets DBpedia and YAGO, and experimental results show that TrQuery exhibits an excellent behavior in terms of both effectiveness and efficiency.

At the conference, Inspur showcased the ODCC standard rack scale server, high-end mission critical 8-way server TS860, OpenPower9 systems, storage optimized server 4U106 Bay servers, and other systems designed for cloud. The full-stack AI solution includes the highest density GPU server -- AGX-2 -- with NVIDIA NVLink enabled, management software AIstation, care-MPI framework and the capability for application optimization. As the world's first NVLink enabled supercomputer with 8 NVIDIA V100 within 2U form factor, the AGX-2 improves the computing efficiency to develop high performance to propel AI, deep learning and advanced analytics development. With over 60% market share, Inspur's rack scale servers are widely used by CSPs such as Alibaba, Baidu, Tencent and 12306 (railway ticket online booking platform). It has set and maintains the record of deploying 10,000 nodes per day.

It seems as if everybody is starting to look at artificial intelligence as some sort of make-or-break technology for the human race. Where the fate of the planet is concerned, there is an increasing collision between the nationalistic view that AI's overriding purpose is to help countries hold their own in geopolitical struggles and the humanitarian view that AI should deliver the benefits of material prosperity to all peoples, serving as an activist force in the universal struggle for equality, free expression, personal autonomy and democratic governance. The nationalistic perspective keeps popping out in headlines. For example, there are the sentiments expressed in this recent article by Horacio Rozanski, chief executive of Booz Allen Hamilton Inc. He discusses what he regards as a "close race" between the United States and China in developing and exploiting AI. I've been exploring AI benchmarking initiatives recently, and I take issue with the assumption that we can validly benchmark one nation against another in this regard.

As humans, we've gotten pretty good at shaping the world around us. We can choose the molecular design of our fruits and vegetables, travel faster and further and stave off life threatening diseases with personalized medical care. However, what continues to elude our molding grasp is the airy notion of "time" – how to see further than our present moment, and ultimately how to make the most of it. As it turns out, robots might be the ones who can answer this question. Computer scientists from the University of Bonn in Germany wrote this week that they were able to design a software that could predict a sequence of events up to five minutes in the future with accuracy between 15 and 40 percent.

With the biggest event in the soccer calendar now underway, fans are speculating on which team might emerge victorious from the 2018 World Cup in Russia – and an artificial intelligence model based on 100,000 simulations has made its prediction too. Using a database of statistics from previous tournaments, and three different AI methods to crunch the numbers, the international team of researchers behind the work thinks Spain is going to emerge victorious... but it's going to be close. At the moment the bookmakers are backing Germany to be World Cup winners, but the AI analysed both the strength of the teams and their route to the final. While Germany would beat Spain in a one-off game, the models showed, the German team is likely to face more difficult opponents through the course of the competition. "By analysing the winning probabilities conditional on reaching the single stages of the tournament, it turns out that the fact that overall Spain is slightly favoured over Germany is mainly due to the fact that Germany has a comparatively high chance to drop out in the round of 16," write the researchers.