Abstract-- We propose two multimodal deep learning architectures that allow for cross-modal dataflow (XFlow) between the feature extractors, thereby extracting more interpretable features and obtaining a better representation than through unimodal learning, for the same amount of training data. These models can usefully exploit correlations between audio and visual data, which have a different dimensionality and are therefore nontrivially exchangeable. Our work improves on existing multimodal deep learning metholodogies in two essential ways: (1) it presents a novel method for performing cross-modality (before features are learned from individual modalities) and (2) extends the previously proposed cross-connections [1], which only transfer information between streams that process compatible data. Both cross-modal architectures outperformed their baselines (by up to 7.5%) when evaluated on the AVletters dataset. I. INTRODUCTION An interesting extension of unimodal learning consists of deep models which "fuse" several modalities (for example, sound, image or text) and thereby learn a shared representation, outperforming previous architectures on discriminative tasks.

In this letter, we propose a new identification criterion that guarantees the recovery of the low-rank latent factors in the nonnegative matrix factorization (NMF) model, under mild conditions. Specifically, using the proposed criterion, it suffices to identify the latent factors if the rows of one factor are \emph{sufficiently scattered} over the nonnegative orthant, while no structural assumption is imposed on the other factor except being full-rank. This is by far the mildest condition under which the latent factors are provably identifiable from the NMF model.

Modeling an ontology is a hard and time-consuming task. Although methodologies are useful for ontologists to create good ontologies, they do not help with the task of evaluating the quality of the ontology to be reused. For these reasons, it is imperative to evaluate the quality of the ontology after constructing it or before reusing it. Few studies usually present only a set of criteria and questions, but no guidelines to evaluate the ontology. The effort to evaluate an ontology is very high as there is a huge dependence on the evaluator's expertise to understand the criteria and questions in depth. Moreover, the evaluation is still very subjective. This study presents a novel methodology for ontology evaluation, taking into account three fundamental principles: i) it is based on the Goal, Question, Metric approach for empirical evaluation; ii) the goals of the methodologies are based on the roles of knowledge representations combined with specific evaluation criteria; iii) each ontology is evaluated according to the type of ontology. The methodology was empirically evaluated using different ontologists and ontologies of the same domain. The main contributions of this study are: i) defining a step-by-step approach to evaluate the quality of an ontology; ii) proposing an evaluation based on the roles of knowledge representations; iii) the explicit difference of the evaluation according to the type of the ontology iii) a questionnaire to evaluate the ontologies; iv) a statistical model that automatically calculates the quality of the ontologies.

Categorical compositional distributional semantics is a model of natural language; it combines the statistical vector space models of words with the compositional models of grammar. We formalise in this model the generalised quantifier theory of natural language, due to Barwise and Cooper. The underlying setting is a compact closed category with bialgebras. We start from a generative grammar formalisation and develop an abstract categorical compositional semantics for it, then instantiate the abstract setting to sets and relations and to finite dimensional vector spaces and linear maps. We prove the equivalence of the relational instantiation to the truth theoretic semantics of generalised quantifiers. The vector space instantiation formalises the statistical usages of words and enables us to, for the first time, reason about quantified phrases and sentences compositionally in distributional semantics.

Despite what you might see in movies, today's robots are still very limited in what they can do. They can be great for many repetitive tasks, but their inability to understand the nuances of human language makes them mostly useless for more complicated requests. For example, if you put a specific tool in a toolbox and ask a robot to "pick it up," it would be completely lost. Picking it up means being able to see and identify objects, understand commands, recognize that the "it" in question is the tool you put down, go back in time to remember the moment when you put down the tool, and distinguish the tool you put down from other ones of similar shapes and sizes. Recently researchers from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) have gotten closer to making this type of request easier: In a new paper, they present an Alexa-like system that allows robots to understand a wide range of commands that require contextual knowledge about objects and their environments.

Humans have not fairly measured ape intelligence, so we don't really understand how smart they are, a team of researchers has asserted. The authors claim that tests are biased such that they measure performance more than they measure actual aptitude, according to a paper in the journal Animal Cognition. Among the problems that make it difficult to test an ape's intelligence in an equitable manner to humans is how differently apes and humans are prepared for experiments -- specifically in their background. This team compares the difference between humans and apes to the differences between different groups of humans. With people, factors like health and education, tied to economics, play a role in how well someone performs on a test designed to measure intelligence.

Many of us will encounter a marketing virtual agent on a near daily basis when being asked qualifying questions or providing automated answers to standard questions, however their potential goes far beyond this and presents exciting opportunities at every stage of the customer journey. Voice assistants create an opportunity to interject compelling content into everyday situations, such as recipes in the kitchen, linked to an ecommerce platform. Recent research has shown that monotonous, repetitive tasks triggers automatic decision making and makes employees more likely to behave unethically. Sure, inertia and lack of technical expertise play a part, but many marketers hold a major question mark over AI's ability to perform a key part of their role: EMPATHY.

Russian President Vladimir Putin says that whoever reaches a breakthrough in developing artificial intelligence will come to dominate the world.... 58 Published By - U.S. News - News - 2017.09.01. Related Posts Opinion: Russia's Vladimir Putin the teacher gets an'F' Deutsche Welle (Yesterday) - Six months before Russia's presidential election, Vladimir Putin wants to show that he's just like everyone else. This time his strategy wound up as a failed attempt to reach out... Teacher arrested for indecent behavior with students Ex-Teacher Sentenced to 12 Years in Case Involving Student Putin Warns North Korea Situation Is on the Verge of a'Large-Scale Conflict' The world may run out of food in a decade New York Post (Yesterday) - The world could be facing a food shortage in just 10 years, according to an agricultural data technology company. Gro Intelligence founder and chief executive Sara Menker says previous calculations... Food revolution in aisle seven: Amazon will be a game ...

It can be difficult to understand how to prepare your sequence data for input to an LSTM model. Often there is confusion around how to define the input layer for the LSTM model. There is also confusion about how to convert your sequence data that may be a 1D or 2D matrix of numbers to the required 3D format of the LSTM input layer. In this tutorial, you will discover how to define the input layer to LSTM models and how to reshape your loaded input data for LSTM models. How to Reshape Input for Long Short-Term Memory Networks in Keras Photo by Global Landscapes Forum, some rights reserved.

A world renowned pioneer in social robotics, Cynthia Breazeal splits her time as an Associate Professor at MIT, where she received her PhD and founded the Personal Robots Group, and Founder and Chief Scientist of Jibo, a personal robotics company with over $85 million in funding. While Breazeal's work has won numerous academic awards, industry accolades, and media attention, she had to fight early skepticism in the 1990s from other experts in robotics and AI. At the time, robots were seen as physical and industrial tools, not social or emotional companions. Her first social robot, Kismet, was unfairly called out in popular press as "useless". Breazeal bucked the trend with a very different vision: "I wanted to create robots with social and emotional intelligence that could work in collaborative partnership with people. In 2-5 years, I see social robots helping families with things that really matter, like education, health, eldercare, entertainment, and companionship." She hopes her work and influence will inspire others to create robots "not only with smarts, but with heart, too."