It used to be that a simple doll or action figure would be a welcome surprise when we tore open our Christmas presents. But now that today's kids grow up in a world saturated with technology, do they expect their toys to be a bit cleverer too? Famous toy retailer Hamleys certainly thinks so, predicting a bumper Christmas for interactive tech toys. So what can we expect? Reyne Rice, chief executive of ToyTrends, actually thinks it's the simpler, educational tech toys that will be the real winners this Christmas.

At Supercomputer 16 (SC16) IBM and NVIDIA have announced what they call the fastest deep learning enterprise solution. The system is based on IBM Power System S822LC platforms that were announced in September. These systems contain the latest version of the IBM POWER8 processor that has NVIDIA NVLink embedded in it. IBM has also released a new deep learning toolkit called IBM PowerAI. The solution is capable of running AlexNet with Caffe up to 2x faster than equivalent systems. It is also capable of outperforming systems running AlexNet with BVLC Caffe using 8 M40 GU-based x86 systems.

Monte Carlo Tree Search (MCTS) is a technique to guide search in a large decision space by taking random samples and evaluating their outcome. In this work, we study MCTS methods in the context of the connection calculus and implement them on top of the leanCoP prover. This includes proposing useful proof-state evaluation heuristics that are learned from previous proofs, and proposing and automatically improving suitable MCTS strategies in this context. The system is trained and evaluated on a large suite of related problems coming from the Mizar proof assistant, showing that it is capable to find new and different proofs. To our knowledge, this is the first time MCTS has been applied to theorem proving.

Benoît Frénay PReCISE Research Center Faculty of Computer Science University of Namur Namur, 5000 - Belgium benoit.frenay@unamur.be In order to be useful, visualizations need to be interpretable. This paper uses a userbased approach to combine and assess quality measures in order to better model user preferences. Results show that cluster separability measures are outperformed by a neighborhood conservation measure, even though the former are usually considered as intuitively representative of user motives. Moreover, combining measures, as opposed to using a single measure, further improves prediction performances.

Gaussian processes (GP) provide a prior over functions and allow finding complex regularities in data. Gaussian processes are successfully used for classification/regression problems and dimensionality reduction. In this work we consider the classification problem only. The complexity of standard methods for GP-classification scales cubically with the size of the training dataset. This complexity makes them inapplicable to big data problems. Therefore, a variety of methods were introduced to overcome this limitation. In the paper we focus on methods based on so called inducing inputs. This approach is based on variational inference and proposes a particular lower bound for marginal likelihood (evidence). This bound is then maximized w.r.t. parameters of kernel function of the Gaussian process, thus fitting the model to data. The computational complexity of this method is $O(nm^2)$, where $m$ is the number of inducing inputs used by the model and is assumed to be substantially smaller than the size of the dataset $n$. Recently, a new evidence lower bound for GP-classification problem was introduced. It allows using stochastic optimization, which makes it suitable for big data problems. However, the new lower bound depends on $O(m^2)$ variational parameter, which makes optimization challenging in case of big m. In this work we develop a new approach for training inducing input GP models for classification problems. Here we use quadratic approximation of several terms in the aforementioned evidence lower bound, obtaining analytical expressions for optimal values of most of the parameters in the optimization, thus sufficiently reducing the dimension of optimization space. In our experiments we achieve as well or better results, compared to the existing method. Moreover, our method doesn't require the user to manually set the learning rate, making it more practical, than the existing method.

Diffuse interface methods have recently been introduced for the task of semi-supervised learning. The underlying model is well-known in materials science but was extended to graphs using a Ginzburg--Landau functional and the graph Laplacian. We here generalize the previously proposed model by a non-smooth potential function. Additionally, we show that the diffuse interface method can be used for the segmentation of data coming from hypergraphs. For this we show that the graph Laplacian in almost all cases is derived from hypergraph information. Additionally, we show that the formerly introduced hypergraph Laplacian coming from a relaxed optimization problem is well suited to be used within the diffuse interface method. We present computational experiments for graph and hypergraph Laplacians.

Functional brain networks are well described and estimated from data with Gaussian Graphical Models (GGMs), e.g. using sparse inverse covariance estimators. Comparing functional connectivity of subjects in two populations calls for comparing these estimated GGMs. Our goal is to identify differences in GGMs known to have similar structure. We characterize the uncertainty of differences with confidence intervals obtained using a parametric distribution on parameters of a sparse estimator. Sparse penalties enable statistical guarantees and interpretable models even in high-dimensional and low-sample settings. Characterizing the distributions of sparse models is inherently challenging as the penalties produce a biased estimator. Recent work invokes the sparsity assumptions to effectively remove the bias from a sparse estimator such as the lasso. These distributions can be used to give confidence intervals on edges in GGMs, and by extension their differences. However, in the case of comparing GGMs, these estimators do not make use of any assumed joint structure among the GGMs. Inspired by priors from brain functional connectivity we derive the distribution of parameter differences under a joint penalty when parameters are known to be sparse in the difference. This leads us to introduce the debiased multi-task fused lasso, whose distribution can be characterized in an efficient manner. We then show how the debiased lasso and multi-task fused lasso can be used to obtain confidence intervals on edge differences in GGMs. We validate the techniques proposed on a set of synthetic examples as well as neuro-imaging dataset created for the study of autism.

Classifiers for the semi-supervised setting often combine strong supervised models with additional learning objectives to make use of unlabeled data. This results in powerful though very complex models that are hard to train and that demand additional labels for optimal parameter tuning, which are often not given when labeled data is very sparse. We here study a minimalistic multi-layer generative neural network for semi-supervised learning in a form and setting as similar to standard discriminative networks as possible. Based on normalized Poisson mixtures, we derive compact and local learning and neural activation rules. Learning and inference in the network can be scaled using standard deep learning tools for parallelized GPU implementation. With the single objective of likelihood optimization, both labeled and unlabeled data are naturally incorporated into learning. Empirical evaluations on standard benchmarks show, that for datasets with few labels the derived minimalistic network improves on all classical deep learning approaches and is competitive with their recent variants without the need of additional labels for parameter tuning. Furthermore, we find that the studied network is the best performing monolithic ('non-hybrid') system for few labels, and that it can be applied in the limit of very few labels, where no other system has been reported to operate so far.

The perceptron [Rosenblatt, 1958] is a conceptually simple and widely used discriminative and linear classification algorithm. It was originally motivated by observations of how signals are passed between neurons in the brain. We will return to the perceptron as a model of neural computation, but from a more technical point of view, the main weakness of the perceptron as a linear classifier is that it is prone to overfitting. One particular type of overfitting that is likely to happen in perceptron learning is feature swamping [Sutton et al., 2006], i.e., that very frequent features may prevent covariant features from being updated, leading to catastrophic performance if the frequent features are absent or less frequent at test time. In other words, in the perceptron, as well as in passive-aggressive learning Crammer et al. [2006], parameters are only updated when features occur, and rare features therefore often receive inaccurate values. There are several ways to approach such overfitting, e.g., capping the model's supremum norm, but here we focus on a specific line of research: confidence-weighted learning of linear classifiers. Confidence-weighted learning explicitly estimates confidence during induction, often by maintaining Gaussian distributions over parameter vectors. In other words, each model parameter is interpreted as a mean, and augmented with a covariance estimate. Confidence-Weighted Learning CWL [Dredze et al., 2008] was the first learning algorithm to do this, but Crammer et al. [2009] later introduced Adaptive Regularization of Weight Vectors (A

An automated army of pro-Donald J. Trump chatbots overwhelmed similar programs supporting Hillary Clinton five to one in the days leading up to the presidential election, according to a report published Thursday by researchers at Oxford University. The chatbots -- basic software programs with a bit of artificial intelligence and rudimentary communication skills -- would send messages on Twitter based on a topic, usually defined on the social network by a word preceded by a hashtag symbol, like #Clinton. Their purpose: to rant, confuse people on facts, or simply muddy discussions, said Philip N. Howard, a sociologist at the Oxford Internet Institute and one of the authors of the report. If you were looking for a real debate of the issues, you weren't going to find it with a chatbot. "And a lot of what they pass around is false news."