Within many machine learning algorithms, a fundamental problem concerns efficient calculation of an unbiased gradient wrt parameters $\gammav$ for expectation-based objectives $\Ebb_{q_{\gammav} (\yv)} [f(\yv)]$. Most existing methods either (i) suffer from high variance, seeking help from (often) complicated variance-reduction techniques; or (ii) they only apply to reparameterizable continuous random variables and employ a reparameterization trick. To address these limitations, we propose a General and One-sample (GO) gradient that (i) applies to many distributions associated with non-reparameterizable continuous or discrete random variables, and (ii) has the same low-variance as the reparameterization trick. We find that the GO gradient often works well in practice based on only one Monte Carlo sample (although one can of course use more samples if desired). Alongside the GO gradient, we develop a means of propagating the chain rule through distributions, yielding statistical back-propagation, coupling neural networks to common random variables.

Matrix profile has been recently proposed as a promising technique to the problem of all-pairs-similarity search on time series. Efficient algorithms have been proposed for computing it, e.g., STAMP, STOMP and SCRIMP++. All these algorithms use the z-normalized Euclidean distance to measure the distance between subsequences. However, as we observed, for some datasets other Euclidean measurements are more useful for knowledge discovery from time series. In this paper, we propose efficient algorithms for computing matrix profile for a general class of Euclidean distances. We first propose a simple but efficient algorithm called AAMP for computing matrix profile with the "pure" (non-normalized) Euclidean distance. Then, we extend our algorithm for the p-norm distance. We also propose an algorithm, called ACAMP, that uses the same principle as AAMP, but for the case of z-normalized Euclidean distance. We implemented our algorithms, and evaluated their performance through experimentation. The experiments show excellent performance results. For example, they show that AAMP is very efficient for computing matrix profile for non-normalized Euclidean distances. The results also show that the ACAMP algorithm is significantly faster than SCRIMP++ (the state of the art matrix profile algorithm) for the case of z-normalized Euclidean distance.

In this work, we study value function approximation in reinforcement learning (RL) problems with high dimensional state or action spaces via a generalized version of representation policy iteration (RPI). We consider the limitations of proto-value functions (PVFs) at accurately approximating the value function in low dimensions and we highlight the importance of features learning for an improved low-dimensional value function approximation. Then, we adopt different representation learning algorithm on graphs to learn the basis functions that best represent the value function. We empirically show that node2vec, an algorithm for scalable feature learning in networks, and the Variational Graph Auto-Encoder constantly outperform the commonly used smooth proto-value functions in low-dimensional feature space.

The traditional Minkowski distances are induced by the corresponding Minkowski norms in real-valued vector spaces. In this work, we propose novel statistical symmetric distances based on the Minkowski's inequality for probability densities belonging to Lebesgue spaces. These statistical Minkowski distances admit closed-form formula for Gaussian mixture models when parameterized by integer exponents. This result extends to arbitrary mixtures of exponential families with natural parameter spaces being cones: This includes the binomial, the multinomial, the zero-centered Laplacian, the Gaussian and the Wishart mixtures, among others. We also derive a Minkowski's diversity index of a normalized weighted set of probability distributions from Minkowski's inequality.

We develop a method that is based on processing gathered Event Related Potentials (ERP) signals and the use of machine learning technique for multivariate analysis (i.e. classification) that we apply in order to analyze the differences between Dyslexic and Skilled readers. No human intervention is needed in the analysis process. This is the state of the art results for automatic identification of Dyslexic readers using a Lexical Decision Task. We use mathematical and machine learning based techniques to automatically discover novel complex features that (i) allow for reliable distinction between Dyslexic and Normal Control Skilled readers and (ii) to validate the assumption that the most of the differences between Dyslexic and Skilled readers located in the left hemisphere. Interestingly, these tools also pointed to the fact that High Pass signals (typically considered as "noise" during ERP/EEG analyses) in fact contains significant relevant information. Finally, the proposed scheme can be used for analysis of any ERP based studies.

Researchers have identified what may be a previously unknown human ancestor, thanks to the help of artificial intelligence. A new investigation into the genome of Asian populations has spotted the footprint of a long-ago hominid that appears to have been bred from two different species of human ancestor – Neanderthal and Denisovan. This ancient hominid, who lived tens of thousands of years ago, then bred with modern humans who arrived to Asia after the'Out of Africa' migration. It comes just months after a different team revealed the discovery of a hybrid'love child' born from a Neanderthal mother and a Denisovan father. And, the new research from the Institute of Evolutionary Biology (IBE), Centro Nacional de Análisis Genómico (CNAG-CRG) of the Centre for Genomic Regulation (CRG), and the Institute of Genomics at the University of Tartu suggests such hominid hybrids may not have been all that uncommon after all.

A hotel in Japan has laid off more than half of its robotic staff following complaints from some guests about the practical limitations of the machines. Among the 243 robots employed by the Henn-na Hotel, which roughly translates as "Weird Hotel" were a velociraptor receptionist, an automated gardener and a one-armed claw that handles left luggage. The facility which made headlines in 2015 when it opened in Nagasaki Prefecture, also made use of more experimental machines, such as bedside table-sized butler capable of arranging a wake up call or announcing the weather forecast. Glitches with this robot saw it wake up guests who were snoring loudly after mistaking the noise for a voice command, The Wall Street Journal reported. The Hen-na hotel describes the concept as "excitement meets comfort" thanks to "state-of-the-art" technologies.

Tech artist Jordan Wolfson is the author of a controversial simulation of virtual reality, explicitly titled Real Violence, in which the viewer, located in New York (United States), observes how the author strikes a man to death. Rachel Rossin manages to take the audience to a point diametrically opposite in Man Mask, a meditation exercise guiding us through the video game Call of Duty: Black Ops without appreciating the slightest sign of aggressiveness. Between the anguish generated by Wolfston's beating and the surrealist paradise of Rossin, there are many examples in which the fundamental innovations of the fourth industrial revolution are put at the service of cultural creation: blockchain, robotics, the internet of things, virtual reality and increased, etc. Alex Reyval became interested in photography in 2012 thanks to drones. Since then he has managed to reflect with his snapshots views that are just unthinkable without the assistance of these unmanned aerial devices. The renowned sculptor Anish Kapoor has come to reduce - virtually - the audience on a microscopic scale so that it can travel the human body.

Data science has become a go-term for almost all the industries, including e-commerce. According to a report by a leading newspaper, India is the fastest growing online retail among the top global economies. With a growth rate of more than 50%, e-commerce websites have become more competitive than ever before. As the competition rises, these e-commerce players are resorting towards the use of technology such as analytics and data science to stay ahead of the competition. With an ever-growing data, it has become crucial for these players to use it in a way to keep the customers happy and satisfies.

Small molecule discovery, binding affinity prediction and medical prescription are the three fields which artificial intelligence seems to have invaded in the pharmaceutical space. Deep Intelligent Pharma (DIP) focuses mainly on building software for providing medical transcription using AI. This Chinese company deploys natural language processing(NLP) frameworks to sift through the exhaustive regulatory documents and assist the pharma companies in manufacturing content which adheres to the law. These AI-enabled writing tools, including automated transcription, tabulated data analysis, document review, and quality control will be used to create content and documents to be submitted to regulatory bodies such as the Food and Drug Administration. The company has raised $26.1 million in funding from Sequoia Capital China and ZhenFund.