Despite recent advances, the remaining bottlenecks in deep generative models are necessity of extensive training and difficulties with generalization from small number of training examples. We develop a new generative model called Generative Matching Network which is inspired by the recently proposed matching networks for one-shot learning in discriminative tasks. By conditioning on the additional input dataset, our model can instantly learn new concepts that were not available in the training data but conform to a similar generative process. The proposed framework does not explicitly restrict diversity of the conditioning data and also does not require an extensive inference procedure for training or adaptation. Our experiments on the Omniglot dataset demonstrate that Generative Matching Networks significantly improve predictive performance on the fly as more additional data is available and outperform existing state of the art conditional generative models.

Vehicle climate control systems aim to keep passengers thermally comfortable. However, current systems control temperature rather than thermal comfort and tend to be energy hungry, which is of particular concern when considering electric vehicles. This paper poses energy-efficient vehicle comfort control as a Markov Decision Process, which is then solved numerically using Sarsa({\lambda}) and an empirically validated, single-zone, 1D thermal model of the cabin. The resulting controller was tested in simulation using 200 randomly selected scenarios and found to exceed the performance of bang-bang, proportional, simple fuzzy logic, and commercial controllers with 23%, 43%, 40%, 56% increase, respectively. Compared to the next best performing controller, energy consumption is reduced by 13% while the proportion of time spent thermally comfortable is increased by 23%. These results indicate that this is a viable approach that promises to translate into substantial comfort and energy improvements in the car.

A constraint satisfaction problem (CSP) is a computational problem where the input consists of a finite set of variables and a finite set of constraints, and where the task is to decide whether there exists a satisfying assignment of values to the variables. Depending on the type of constraints that we allow in the input, a CSP might be tractable, or computationally hard. In recent years, general criteria have been discovered that imply that a CSP is polynomial-time tractable, or that it is NP-hard. Finite-domain CSPs have become a major common research focus of graph theory, artificial intelligence, and finite model theory. It turned out that the key questions for complexity classification of CSPs are closely linked to central questions in universal algebra. This thesis studies CSPs where the variables can take values from an infinite domain. This generalization enhances dramatically the range of computational problems that can be modeled as a CSP. Many problems from areas that have so far seen no interaction with constraint satisfaction theory can be formulated using infinite domains, e.g. problems from temporal and spatial reasoning, phylogenetic reconstruction, and operations research. It turns out that the universal-algebraic approach can also be applied to study large classes of infinite-domain CSPs, yielding elegant complexity classification results. A new tool in this thesis that becomes relevant particularly for infinite domains is Ramsey theory. We demonstrate the feasibility of our approach with two complete complexity classification results: one on CSPs in temporal reasoning, the other on a generalization of Schaefer's theorem for propositional logic to logic over graphs. We also study the limits of complexity classification, and present classes of computational problems provably do not exhibit a complexity dichotomy into hard and easy problems.

We discuss the computational complexity of approximating maximum a posteriori inference in sum-product networks. We first show NP-hardness in trees of height two by a reduction from maximum independent set; this implies non-approximability within a sublinear factor. We show that this is a tight bound, as we can find an approximation within a linear factor in networks of height two. We then show that, in trees of height three, it is NP-hard to approximate the problem within a factor $2^{f(n)}$ for any sublinear function $f$ of the size of the input $n$. Again, this bound is tight, as we prove that the usual max-product algorithm finds (in any network) approximations within factor $2^{c \cdot n}$ for some constant $c < 1$. Last, we present a simple algorithm, and show that it provably produces solutions at least as good as, and potentially much better than, the max-product algorithm. We empirically analyze the proposed algorithm against max-product using synthetic and realistic networks.

Researchers have long thought that being able to recognize faces is innate in humans and other primates, and that something in our brains just knows how to do this from birth. But a new brain imaging study suggests otherwise - macaques need to have been exposed to faces from a young age to be able to recognize faces. The findings shed light on a range of neuro-developmental conditions, including those in which people can't distinguish between different faces or autism, which is marked by aversion to looking at faces. By 200 days of age, macaques form clusters of neurons responsible for recognizing faces in an area of the brain called the superior temporal sulcus. To better understand the basis for facial recognition, Harvard Medical School researchers raised two groups of macaques.

KG: Starting from the beginning, what is statistics and how did it come about? Could you give us a short definition and history of the discipline? In a brief nutshell statistics began as a way to understand the workings of states, productivity, life expectancy, agricultural yields, etc., and to make estimates of things from samples (an statistical example of the latter dates back to the 5th century BCE in Athens). Concerning a definition for statistics, it is a field that is a science unto itself and that benefits all other fields and everyday life. What is unique about statistics is its proven tools for decision making in the face of uncertainty, understanding sources of variation and bias, and most importantly, statistical thinking.

Americans aged 30-44 are most eager to rely on artificial intelligence but they'd rather it was used to do their cleaning over flying a plane. According to a poll conducted by Morning Consult, more than half of people (57 per cent) already realise that they come across AI in their daily lives. The poll, conducted with 2,200 adults, found that more people (41 per cent) believe that AI is safe compared to 38 per cent who think it unsafe. Despite that levels of fear, it seems as if Americans are keen to hand over simple labour-intensive tasks such as cleaning to robots. When it comes to more complex tasks, people are less trusting, with three out of five people uncomfortable with AI making financial investments.

Machine learning gives you unimaginably powerful insights into data. Today, implementations of machine learning have been adopted throughout Industry and its concepts are numerous. This video is a unique blend of projects that teach you what Machine Learning is all about and how you can implement machine learning concepts in practice. Six different independent projects will help you master machine learning in Python. The video will cover concepts such as classification, regression, clustering, and more, all the while working with different kinds of databases.

Men and women take selfies from different angles, and a new study suggests the psychology of attraction is the reason why. Researchers from Florida State University say selfie-takers manipulate camera angles when taking photos of themselves as an'impression-management strategy'. Men take them head-on to attract women, or from below to appear dominant to other men, while women take photos from above to appear more attractive to men. Researchers from Florida State University found selfie-takers manipulate camera angles when taking photos of themselves as an impression-management strategy. Nastasia Makhanova and her team at Florida State University found selfie-takers manipulate camera angles when taking photos of themselves as an impression-management strategy.

Artificial intelligence can pick up on symptoms of Alzheimer's disease in brain scans long before doctors or patients. A computer-driven algorithm was able to accurately foresee whether or not a person would develop Alzheimer's disease up to two years before he or she displays symptoms, according to a new study from McGill University. It was correct in its predictions 84% of the time. Researchers are excited for the AI's potential to help choose patients for clinical trials and drugs ahead of the disease's onset that could delay its debilitating effects. "If you can tell from a group of individuals who is the one that will develop the disease, one can better test new medications that could be capable or preventing the disease," Dr. Pedro Rosa-Neto, a study co-author, told Live Science.