Embedded Intelligence, German Research Center for Artificial Intelligence, Kaiserslautern, Germany, {vitor.fortes,paul.lukowicz}@dfki.de Abstract Traditional activity recognition systems work on the basis of training, taking a fixed set of sensors into account. In this article, we focus on the question how pattern recognition can leverage new information sources without any, or with minimal user input. Thus, we present an approach for opportunistic activity recognition, where ubiquitous sensors lead to dynamically changing input spaces. Our method is a variation of well-established principles of machine learning, relying on unsupervised clustering to discover structure in data and inferring cluster labels from a small number of labeled dates in a semi-supervised manner. Elaborating the challenges, evaluations of over 3000 sensor combinations from three multiuser experiments are presented in detail and show the potential benefit of our approach. Keywords: Opportunistic Activity Recognition, Unsupervised Learning, Semi-supervised Learning, Classifier Adaptation 1. Introduction Today, state-of-the-art approaches to activity and context recognition typically assume fixed, narrowly defined system configurations dedicated to often also narrowly defined tasks. Such systems can only work when sensors are known in the training phase and they cannot adapt to new sensors in their environment. In turn, sensors are evermore present in our life, although not always available. When moving around, a person may face highly instrumented environments and places with little or no intelligent infrastructure. Concerning on-body sensing, a user may carry a varying collection of sensor enabled devices (mobile phone, watch, headset, etc.) on different, dynamically varying body locations (different pockets, wrist, bag). Thus, in order to realize their full potential, systems need to take advantage of devices that just "happen" to be in the environment, taking into account their current placement and relevance. In our previous work, we investigated how on-body position and orientation of on-body sensors can be inferred [1, 2], how position shifts can be tolerated [3], and how one sensor can replace another [4]. Preprint submitted to Computational Intelligence and Neuroscience March 15, 2018 integration. More precisely, this means to answer the question how can a new sensor's data be integrated in an existing activity recognition system at runtime in order to improve this recognition process. Extending a system that used n sensors to one that uses (n 1) has many challenges. For instance, training data is expensive, and thus we cannot expect the new (n 1) data to be labeled.

Bayesian network models with latent variables are widely used in statistics and machine learning. In this paper we provide a complete algebraic characterization of Bayesian network models with latent variables when the observed variables are discrete and no assumption is made about the state-space of the latent variables. We show that it is algebraically equivalent to the so-called nested Markov model, meaning that the two are the same up to inequality constraints on the joint probabilities. In particular these two models have the same dimension. The nested Markov model is therefore the best possible description of the latent variable model that avoids consideration of inequalities, which are extremely complicated in general. A consequence of this is that the constraint finding algorithm of Tian and Pearl (UAI 2002, pp519-527) is complete for finding equality constraints. Latent variable models suffer from difficulties of unidentifiable parameters and non-regular asymptotics; in contrast the nested Markov model is fully identifiable, represents a curved exponential family of known dimension, and can easily be fitted using an explicit parameterization.

Future projection of climate is typically obtained by combining outputs from multiple Earth System Models (ESMs) for several climate variables such as temperature and precipitation. While IPCC has traditionally used a simple model output average, recent work has illustrated potential advantages of using a multitask learning (MTL) framework for projections of individual climate variables. In this paper we introduce a framework for hierarchical multitask learning (HMTL) with two levels of tasks such that each super-task, i.e., task at the top level, is itself a multitask learning problem over sub-tasks. For climate projections, each super-task focuses on projections of specific climate variables spatially using an MTL formulation. For the proposed HMTL approach, a group lasso regularization is added to couple parameters across the super-tasks, which in the climate context helps exploit relationships among the behavior of different climate variables at a given spatial location. We show that some recent works on MTL based on learning task dependency structures can be viewed as special cases of HMTL. Experiments on synthetic and real climate data show that HMTL produces better results than decoupled MTL methods applied separately on the super-tasks and HMTL significantly outperforms baselines for climate projection.

Over the past decade, the stellar growth of Indian economy has been challenged by persistently high levels of inflation, particularly in food prices. The primary reason behind this stubborn food inflation is mismatch in supply-demand, as domestic agricultural production has failed to keep up with rising demand owing to a number of proximate factors. The relative significance of these factors in determining the change in food prices have been analysed using gradient boosted regression trees (BRT) - a machine learning technique. The results from BRT indicates all predictor variables to be fairly significant in explaining the change in food prices, with MSP and farm wages being relatively more important than others. International food prices were found to have limited relevance in explaining the variation in domestic food prices. The challenge of ensuring food and nutritional security for growing Indian population with rising incomes needs to be addressed through resolute policy reforms.

Chernozhukov, Chetverikov, Demirer, Duflo, Hansen, and Newey (2016) provide a generic double/debiased machine learning (DML) approach for obtaining valid inferential statements about focal parameters, using Neyman-orthogonal scores and cross-fitting, in settings where nuisance parameters are estimated using a new generation of nonparametric fitting methods for high-dimensional data, called machine learning methods. In this note, we illustrate the application of this method in the context of estimating average treatment effects (ATE) and average treatment effects on the treated (ATTE) using observational data. A more general discussion and references to the existing literature are available in Chernozhukov, Chetverikov, Demirer, Duflo, Hansen, and Newey (2016). Key words: Neyman machine learning, orthogonalization, cross-fitting, double or de-biased machine learning, orthogonal score, efficient score, post-machine-learning and post-regularization inference, random forest, lasso, deep learning, neural nets, boosted trees, efficiency, optimality.

Owing to the data deluge and the Cambrian explosion of machine learning techniques over the past decade, one might have expected the transformation of marketing strategy into a predominantly quantitative discipline by now. The fact that it hasn't happened yet, and the observation that marketing is still influenced by a lot of qualitative inputs can be ascribed to two reasons, in my opinion. The first and principal reason continues to be institutional inertia. Second, there is a significant communication and knowledge gap between data scientists and marketers, owing to their relative lack of familiarity with the other side's perspectives and paradigms. The successful marketer of the next decade is someone who is conversant with management theories of Kotler[1] as well as machine learning advances by Hinton[2]/LeCun[3]/ Ng[4].

Arthur C. Clarke famously stated that "any sufficiently advanced technology is indistinguishable from magic." No current technology embodies this statement more than neural networks and deep learning. And like any good magic it not only dazzles and inspires but also puts fear into people's hearts. One known property of artificial neural networks (ANNs) is that they are universal function approximators. This means that any mathematical function can be represented by a neural network.

Attributes of Participatory Culture @TransformSoc (Henry Jenkins) • Affiliations: online communities • Expressions: new creative forms • Collaborations: Problem-solving in teams • Circulations: Shaping media flow Source: Confronting The Challenges Of Participatory Culture, by Henry Jenkins, MIT Press, 2009 31.

Do you think you can tell a piece of music composed by artificial intelligence (AI) from one created by a human composer? Before you read any further, let's find out. The following audio consists of two fragments, one written by AI, the other by a human. If you didn't get it right the first time, no worries--we'll have a couple more mini-quizzes like this below. The AI that wrote the fragment above has been programmed by Jukedeck, a UK-based startup working on machine-made music that won the competition at TechCrunch Disrupt London in 2015.

Persistence Market Research delivers pertinent insights on the growth of the Cognitive Computing Market and identifies key market dynamics impacting this growth. New York City, NY -- (SBWIRE) -- 01/27/2017 -- In the ever changing world of information technology, business organizations are left with humongous amount of data with them. This data includes very critical information for business use, but business organizations are only able to utilize 20% of whole data available with them with the use of traditional data analytics technology. To process and interpret the reaming 80% of the data that is in the form of videos, images, and human voice (also called as dark data), there is a need of cognitive computing systems. Cognitive computing systems are typical combination of hardware and software that constitute natural language processing (NLP) and machine language, and have capability to collect, process, and interpret the dark data available with business organizations.