Among the innovations pioneered by John White during his years as CEO of ACM was a new relationship with the Klaus Tschira Foundation that sponsors the Heidelberg Laureate Foruma [HLF] in the third quarter of each year. The attendees include about 200 math or computer science students and recipients of the mathematics Fields Medal, the Nevanlinna Prize, the Abel Prize, and ACM's A.M. Turing award for computer science. I have had the pleasure of attending the first three meetings of the HLF. Since 1951, however, there has been an annual meeting of Nobel laureatesb with support from several organizations including the aforementioned Klaus Tschira Foundation. The HLF is patterned after the Nobel meeting: students meet with a collection of participating laureates. It was decided last year to link these two events by having a Nobel laureate address the participants of the HLF and to have an HLF laureate address the participants of the Nobel annual meeting.

The ultimate goals of serious education games (SEG) are to facilitate learning and maximizing enjoyment during playing SEGs. In SEG development, there are normally two spaces to be taken into account: knowledge space regarding learning materials and content space regarding games to be used to convey learning materials. How to deploy the learning materials seamlessly and effectively into game content becomes one of the most challenging problems in SEG development. Unlike previous work where experts in education have to be used heavily, we proposed a novel approach that works toward minimizing the efforts of education experts in mapping learning materials to content space. For a proof-of-concept, we apply the proposed approach in developing an SEG game, named \emph{Chem Dungeon}, as a case study in order to demonstrate the effectiveness of our proposed approach. This SEG game has been tested with a number of users, and the user survey suggests our method works reasonably well.

Community detection has been an active research area for decades. Among all probabilistic models, Stochastic Block Model has been the most popular one. This paper introduces a novel probabilistic model: RW-HDP, based on random walks and Hierarchical Dirichlet Process, for community extraction. In RW-HDP, random walks conducted in a social network are treated as documents; nodes are treated as words. By using Hierarchical Dirichlet Process, a nonparametric Bayesian model, we are not only able to cluster nodes into different communities, but also determine the number of communities automatically. We use Stochastic Variational Inference for our model inference, which makes our method time efficient and can be easily extended to an online learning algorithm.

The Event Calculus is a temporal logic that has been used as a basis in event recognition applications, providing among others, direct connections to machine learning, via Inductive Logic Programming (ILP). We present an ILP system for online learning of Event Calculus theories. To allow for a single-pass learning strategy, we use the Hoeffding bound for evaluating clauses on a subset of the input stream. We employ a decoupling scheme of the Event Calculus axioms during the learning process, that allows to learn each clause in isolation. Moreover, we use abductive-inductive logic programming techniques to handle unobserved target predicates. We evaluate our approach on an activity recognition application and compare it to a number of batch learning techniques. We obtain results of comparable predicative accuracy with significant speed-ups in training time. We also outperform hand-crafted rules and match the performance of a sound incremental learner that can only operate on noise-free datasets. This paper is under consideration for acceptance in TPLP.

Statistical inference on graphs is a burgeoning field of research in machine learning and statistics, with numerous applications to social network, neuroscience, etc. Many statistical inference procedures for graphs involve a preprocessing step of finding a representation of the vertices as points in some low-dimensional Euclidean space. This representation is usually given by the truncated eigendecomposition of the adjacency matrix or related matrices such as the combinatorial Laplacian or the normalized Laplacian. For example, given a point cloud lying in some purported low-dimensional manifold in a high-dimensional ambient space, many manifold learning or nonlinear dimension reduction algorithms such as Laplacian eigenmaps [5] and diffusion maps [15] use the eigenvectors of the normalized Laplacian constructed from a neighborhood graph of the points as a low-dimensional Euclidean representation of the point cloud before performing inference such as clustering or classification. Spectral clustering 1 algorithms such as the normalized cuts algorithm [35] proceed by embedding a graph into a low-dimensional Euclidean space followed by running K-means on the embedding to obtain a partitioning of the vertices.

This paper addresses classification tasks on a particular target domain in which labeled training data are only available from source domains different from (but related to) the target. Two closely related frameworks, domain adaptation and domain generalization, are concerned with such tasks, where the only difference between those frameworks is the availability of the unlabeled target data: domain adaptation can leverage unlabeled target information, while domain generalization cannot. We propose Scatter Component Analyis (SCA), a fast representation learning algorithm that can be applied to both domain adaptation and domain generalization. SCA is based on a simple geometrical measure, i.e., scatter, which operates on reproducing kernel Hilbert space. SCA finds a representation that trades between maximizing the separability of classes, minimizing the mismatch between domains, and maximizing the separability of data; each of which is quantified through scatter. The optimization problem of SCA can be reduced to a generalized eigenvalue problem, which results in a fast and exact solution. Comprehensive experiments on benchmark cross-domain object recognition datasets verify that SCA performs much faster than several state-of-the-art algorithms and also provides state-of-the-art classification accuracy in both domain adaptation and domain generalization. We also show that scatter can be used to establish a theoretical generalization bound in the case of domain adaptation.

Estimating the gradient of a given function (with or without noise) is often an important part of problems in reinforcement learning, optimization and manifold learning. In reinforcement learning, policy-gradient methods are used to obtain an unbiased estimator for the gradient. The policy parameters are then updated with increments proportional to the estimated gradient [27]. The objective is to learn a locally optimum policy. REINFORCE and PGPE methods (policy gradients with parameter-based exploration) are popular instances of this approach (See [35] for details and comparisons, [13] for a survey on policy gradient methods in the context of actor-critic algorithms).

LONDON: As you're choking down your latest serving of Trump Clinton Brexit Racism Terrorism Wealth Gap Climate Change Casserole, you could use some good news. Let's start with The Inevitable, the new best-seller by Kevin Kelly, the founder of Wired magazine some 20 years ago and one of our wisest technological prognosticators. "This is the moment that folks in the future will look back at and say, 'Oh to have been alive and well back then!'" Kelly writes. "There has never been a better time with more opportunities, more openings, lower barriers, higher benefit/risk ratios, better returns, greater upside than now. In the mid-2010s, we're getting the first sneak peeks at a bouquet of technologies that can vastly improve the lives of most people on the planet and solve some of our hardest problems – even climate change.

A more elaborate rule-based bot might feed off a much larger data set. For example, if you connected a bot up to Wikipedia you could program it to respond to commonly formulated questions like'when was...' or'who is...' with appropriate information. Or imagine it connected to Wolfram Alpha, a service that can already offer meaningful answers, next steps, and supplementary information when asked questions like'what is the Battle of Hastings' or'what is the square root of 67567899986677654444332'. If you have an Apple device you might have noticed that Siri relies on Wolfram Alpha for some of it's answers - this stuff is happening right now.

Say hello to Nadine, a "receptionist" at Nanyang Technological University (NTU Singapore). She is friendly, and will greet you back. Next time you meet her, she will remember your name and your previous conversation with her. She looks almost like a human being, with soft skin and flowing brunette hair. She smiles when greeting you, looks at you in the eye when talking, and can also shake hands with you. And she is a humanoid.