Descriptive titles provide crucial context for interpreting tables that are extracted from web pages and are a key component of table-based web applications. Prior approaches have attempted to produce titles by selecting existing text snippets associated with the table. These approaches, however, are limited by their dependence on suitable titles existing a priori. In our user study, we observe that the relevant information for the title tends to be scattered across the page, and often---more than 80% of time---does not appear verbatim anywhere in the page. We propose instead the application of a sequence-to-sequence neural network model as a more generalizable means of generating high-quality titles. This is accomplished by extracting many text snippets that have potentially relevant information to the table, encoding them into an input sequence, and using both copy and generation mechanisms in the decoder to balance relevance and readability of the generated title. We validate this approach with human evaluation on sample web tables and report that while sequence models with only a copy mechanism or only a generation mechanism are easily outperformed by simple selection-based baselines, the model with both capabilities outperforms them all, approaching the quality of crowdsourced titles while training on fewer than ten thousand examples. To the best of our knowledge, the proposed technique is the first to consider text-generation methods for table titles, and establishes a new state of the art.

We introduce TextWorld, a sandbox learning environment for the training and evaluation of RL agents on text-based games. TextWorld is a Python library that handles interactive play-through of text games, as well as backend functions like state tracking and reward assignment. It comes with a curated list of games whose features and challenges we have analyzed. More significantly, it enables users to handcraft or automatically generate new games. Its generative mechanisms give precise control over the difficulty, scope, and language of constructed games, and can be used to relax challenges inherent to commercial text games like partial observability and sparse rewards. By generating sets of varied but similar games, TextWorld can also be used to study generalization and transfer learning. We cast text-based games in the Reinforcement Learning formalism, use our framework to develop a set of benchmark games, and evaluate several baseline agents on this set and the curated list.

Generative adversarial networks (GANs) are a novel approach to generative modelling, a task whose goal it is to learn a distribution of real data points. They have often proved difficult to train: GANs are unlike many techniques in machine learning, in that they are best described as a two-player game between a discriminator and generator. This has yielded both unreliability in the training process, and a general lack of understanding as to how GANs converge, and if so, to what. The purpose of this dissertation is to provide an account of the theory of GANs suitable for the mathematician, highlighting both positive and negative results. This involves identifying the problems when training GANs, and how topological and game-theoretic perspectives of GANs have contributed to our understanding and improved our techniques in recent years.

We present an OWL 2 ontology representing the Saint Gall plan, one of the most ancient documents arrived intact to us, which describes the ideal model of a Benedictine monastic complex that inspired the design of many European monasteries.

Human cognition is a complex process facilitated by the intricate architecture of human brain. However, human cognition is often reduced to quantum theory based events in principle because of their correlative conjectures for the purpose of analysis for reciprocal understanding. In this paper, we begin our analysis of human cognition via formal methods and proceed towards quantum theories. Human cognition often violate classic probabilities on which formal representation of conceptual spaces are built. Further, geometric representation of conceptual spaces proposed by Gardenfors discusses the underlying content but lacks a systematic approach (Gardenfors, 2000; Kitto et. al, 2012). However, the aforementioned views are not contradictory but different perspective with a gap towards sufficient understanding of human cognitive process. A comprehensive and systematic approach to model a relatively complex scenario can be addressed by vector space approach of conceptual spaces as discussed in literature. In this research, we have proposed an approach that uses both formal representation and Gardenfors geometric approach. The proposed model of high dimensional formal representation of conceptual space is mathematically analysed and inferred to exhibit quantum aspects. Also, the proposed model achieves cognition, in particular, consciousness. We have demonstrated this process of achieving consciousness with a constructive learning scenario. We have also proposed an algorithm for conceptual scaling of a real world scenario under different quality dimensions to obtain a conceptual scale.

Bayesian methods in machine learning, such as Gaussian processes, have great advantages compared to other techniques. In particular, they provide estimates of the uncertainty associated with a prediction. Extending the Bayesian approach to deep architectures has remained a major challenge. Recent results connected deep feedforward neural networks with Gaussian processes, allowing training without backpropagation. This connection enables us to leverage a quantum algorithm designed for Gaussian processes and develop new algorithms for Bayesian deep learning on quantum computers. The properties of the kernel matrix in the Gaussian process ensure the efficient execution of the core component of the protocol, quantum matrix inversion, providing a polynomial speedup with respect to classical algorithm. Furthermore, we demonstrate the execution of the algorithm on contemporary quantum computers and analyze its robustness to realistic noise models.

Following a number of years during which robotic process automation (RPA) was something only a relatively small number of companies had yet dabbled in, notable progress is now evident, a new report suggests. In a survey of 500 senior finance executives in North America and Europe by technology and outsourcing consulting firm Capgemini, 41% said their organization has an enterprise-wide automation strategy in place. Finance is leading the way -- something that the report acknowledges may be counterintuitive for IT professionals. "After all, back-office functions are not often the first to benefit from investment in advanced digital technologies," the report states. "But the era of intelligent automation provides a way to change that."

LONDON (Reuters) - London-based Babylon Health says its artificial intelligence technology, in tests, has outperformed most physicians in assessing disease symptoms, throwing down a challenge to doctors, some of whom doubt its true abilities. Babylon, which was founded by entrepreneur Ali Parsa in 2013, is one of a number of start-ups tapping into the promise of artificial intelligence (AI) to help patients and doctors sift through symptoms to come up with a diagnosis. It aims to offer health advice of family doctor quality by using AI delivered through a smartphone chatbot app - potentially a big saving for governments as they struggle to fund healthcare for growing and ageing populations. In a representative sample of questions set by the Royal College of General Practitioners (RCGP) for its final exams to qualify as a family doctor, the Babylon app achieved an 81 percent success level, well ahead of the average pass mark over the last five years of 72 percent, the company said. But Martin Marshall, vice chairman of the RCGP, said AI systems could not be compared to highly-trained medical professionals.

Babylon Health founder Ali Parsa presenting the results of his AI-powered medical information software, which took a standard doctor's exam. The lights were dimmed in an auditorium packed with doctors on Wednesday night at London's Royal College of Physicians. They were there to find out how AI might fundamentally change the way they work. On stage Dr. Mobasher Butt, a director at digital healthcare startup Babylon Health, stood before a podium to read out the results of an exam taken by his company's carefully trained AI doctor. The average passmark for the MRCGP exam, which trainee general practitioners take to test their ability to diagnose, has been 72% over the past five years.

Recently, we visited The Data Science Economy conference in Zagreb. More than 30 speakers covered a lot of real-life use cases, best practices, and future trends in the field of Data Science. We also participated in "Deep Dive into Deep Learning„ workshop held by Leonardo De Marchi, the Lead Data Scientist in Badoo (Badoo is the largest dating site with over 360 million users). As the Deep Learning is part of our daily work and also the main trend in AI, we decided to share with you some of the insights we learned at this workshop and help you to start your own first deep learning project. We will go through some of the basic Deep Learning concepts with Keras.