Chintu, the robot, slowly sat down on the floor, with both hands resting on its knees. Then, on command, it stood up, using one hand for support. The 58-centimetre-tall robot, manufactured by Softbank Robotics of France and owned by Maharashtra Institute of Technology (MIT), Pune, was one of the attractions of IBM Cloud Forum, a jamboree of companies using IBM's cloud and machine learning (ML) solutions in the last week of May in Mumbai. Alongside Chintu were its guardians -- Astitva Shah and Krishnamohan M, final-year engineering students from MIT, Pune. The duo have been working on a project to develop Chintu as an assistant for elderly people who are living alone.

By tracking cursor movement, lie detection becomes a game of cat and mouse. Every year, millions of people have their identities stolen. There's no foolproof way to pinpoint fakers, but thanks to Italian researchers, investigators may soon have another tool at their disposal--a way to suss out frauds and other liars online with just a few clicks of a mouse. Traditional methods of lie detection include face-to-face interviews and polygraphs that measure heart rate and skin conductance. But they can't be done remotely, or with large numbers of people.

The standard Kernel Quadrature method for numerical integration with random point sets (also called Bayesian Monte Carlo) is known to converge in root mean square error at a rate determined by the ratio $s/d$, where $s$ and $d$ encode the smoothness and dimension of the integrand. However, an empirical investigation reveals that the rate constant $C$ is highly sensitive to the distribution of the random points. In contrast to standard Monte Carlo integration, for which optimal importance sampling is well-understood, the sampling distribution that minimises $C$ for Kernel Quadrature does not admit a closed form. This paper argues that the practical choice of sampling distribution is an important open problem. One solution is considered; a novel automatic approach based on adaptive tempering and sequential Monte Carlo. Empirical results demonstrate a dramatic reduction in integration error of up to 4 orders of magnitude can be achieved with the proposed method.

Abstract--A multiple instance dictionary learning approach, Dictionary Learning using Functions of Multiple Instances (DL-FUMI), is used to perform beat-to-beat heart rate estimation and to characterize heartbeat signatures from ballistocardiogram (BCG) signals collected with a hydraulic bed sensor. DL-FUMI estimates a "heartbeat concept" that represents an individual's personal ballistocardiogram heartbeat pattern. DL-FUMI formulates heartbeat detection and heartbeat characterization as a multiple instance learning problem to address the uncertainty inherent in aligning BCG signals with ground truth during training. Experimental results show that the estimated heartbeat concept found by DL-FUMI is an effective heartbeat prototype and achieves superior performance over comparison algorithms. I. INTRODUCTION Increasingly more and more devices for realtime heart rate monitoring are becoming available. However, the majority of these devices are intrusive and require continual interaction. For example many heart rate monitoring systems require a user to physically wear the system ( e.g., as a watch, chest strap, electrodes, finger sensor, etc.) and/or charge batteries frequently. In contrast, devices that use ballistocardiography can provide an unintrusive and, thus, relatively low maintenance, comfortable alternative for heart rate monitoring. These sensing systems record the motion of the human body generated by the sudden ejection of blood into the large vessels at each cardiac cycle [1]. Such motion contains rich information and has gained revived interest due to recent development in measurement technology [2, 3] and a growing interest in managing chronic health conditions through passive sensors in the home [4].

We consider the problem of quickest change-point detection in data streams. Classical change-point detection procedures, such as CUSUM, Shiryaev-Roberts and Posterior Probability statistics, are optimal only if the change-point model is known, which is an unrealistic assumption in typical applied problems. Instead we propose a new method for change-point detection based on Inductive Conformal Martingales, which requires only the independence and identical distribution of observations. We compare the proposed approach to standard methods, as well as to change-point detection oracles, which model a typical practical situation when we have only imprecise (albeit parametric) information about pre- and post-change data distributions. Results of comparison provide evidence that change-point detection based on Inductive Conformal Martingales is an efficient tool, capable to work under quite general conditions unlike traditional approaches.

Anomalies in time-series data give essential and often actionable information in many applications. In this paper we consider a model-free anomaly detection method for univariate time-series which adapts to non-stationarity in the data stream and provides probabilistic abnormality scores based on the conformal prediction paradigm. Despite its simplicity the method performs on par with complex prediction-based models on the Numenta Anomaly Detection benchmark and the Yahoo!

The success of automated driving deployment is highly depending on the ability to develop an efficient and safe driving policy. The problem is well formulated under the framework of optimal control as a cost optimization problem. Model based solutions using traditional planning are efficient, but require the knowledge of the environment model. On the other hand, model free solutions suffer sample inefficiency and require too many interactions with the environment, which is infeasible in practice. Methods under the Reinforcement Learning framework usually require the notion of a reward function, which is not available in the real world. Imitation learning helps in improving sample efficiency by introducing prior knowledge obtained from the demonstrated behavior, on the risk of exact behavior cloning without generalizing to unseen environments. In this paper we propose a Meta learning framework, based on data set aggregation, to improve generalization of imitation learning algorithms. Under the proposed framework, we propose MetaDAgger, a novel algorithm which tackles the generalization issues in traditional imitation learning. We use The Open Race Car Simulator (TORCS) to test our algorithm. Results on unseen test tracks show significant improvement over traditional imitation learning algorithms, improving the learning time and sample efficiency in the same time. The results are also supported by visualization of the learnt features to prove generalization of the captured details.

The vast majority of theoretical results in machine learning and statistics assume that the available training data is a reasonably reliable reflection of the phenomena to be learned or estimated. Similarly, the majority of machine learning and statistical techniques used in practice are brittle to the presence of large amounts of biased or malicious data. In this work we consider two frameworks in which to study estimation, learning, and optimization in the presence of significant fractions of arbitrary data. The first framework, list-decodable learning, asks whether it is possible to return a list of answers, with the guarantee that at least one of them is accurate. For example, given a dataset of $n$ points for which an unknown subset of $\alpha n$ points are drawn from a distribution of interest, and no assumptions are made about the remaining $(1-\alpha)n$ points, is it possible to return a list of $\operatorname{poly}(1/\alpha)$ answers, one of which is correct? The second framework, which we term the semi-verified learning model, considers the extent to which a small dataset of trusted data (drawn from the distribution in question) can be leveraged to enable the accurate extraction of information from a much larger but untrusted dataset (of which only an $\alpha$-fraction is drawn from the distribution). We show strong positive results in both settings, and provide an algorithm for robust learning in a very general stochastic optimization setting. This general result has immediate implications for robust estimation in a number of settings, including for robustly estimating the mean of distributions with bounded second moments, robustly learning mixtures of such distributions, and robustly finding planted partitions in random graphs in which significant portions of the graph have been perturbed by an adversary.

If you think you're seeing more on the topic of artificial intelligence in marketing lately, there's a reason--you are. In fact, a new study by Weber Shandwick finds that the majority of CMOs in five global markets believe artificial intelligence (AI) will surpass social media's influence in the industry. According to the 150 senior executives surveyed, 55% believe that AI will transform the marketing and communications world even more than social media, and 68% say that their brand is currently selling, using, or planning for business in the era of AI. When we think about artificial intelligence, we think about Siri, Arnold Swarzeneeger's character in The Terminator, or IBM's Watson, which recently defeated the two greatest Jeopardy champions and "stole" the $1 million prize. But AI is being used for practical ways that, as marketers, affect us all.

It is midnight on January 18, 2017, and the Outbrain Click Prediction machine learning competition has just finished. It has been three and a half months of working late. As I scroll through the leaderboard page, I found my name in the 19th position, which was the top 2% from nearly 1,000 competitors. Not bad for the first Kaggle competition I had decided to put a real effort in! One of the reasons why I managed to score well was the fact that Google Cloud Platform (GCP) made my life easier and I could focus on the data.