Conversational systems have become increasingly popular as a way for humans to interact with computers. To be able to provide intelligent responses, conversational systems must correctly model the structure and semantics of a conversation. We introduce the task of measuring semantic (in)coherence in a conversation with respect to background knowledge, which relies on the identification of semantic relations between concepts introduced during a conversation. We propose and evaluate graph-based and machine learning-based approaches for measuring semantic coherence using knowledge graphs, their vector space embeddings and word embedding models, as sources of background knowledge. We demonstrate how these approaches are able to uncover different coherence patterns in conversations on the Ubuntu Dialogue Corpus.

The dominant, state-of-the-art collaborative filtering (CF) methods today mainly comprises neural models. In these models, deep neural networks, e.g.., multi-layered perceptrons (MLP), are often used to model nonlinear relationships between user and item representations. As opposed to shallow models (e.g., factorization-based models), deep models generally provide a greater extent of expressiveness, albeit at the expense of impaired/restricted information flow. Consequently, the performance of most neural CF models plateaus at 3-4 layers, with performance stagnating or even degrading when increasing the model depth. As such, the question of how to train really deep networks in the context of CF remains unclear. To this end, this paper proposes a new technique that enables training neural CF models all the way up to 20 layers and beyond. Our proposed approach utilizes a new hierarchical self-attention mechanism that learns introspective intra-feature similarity across all the hidden layers of a standard MLP model. All in all, our proposed architecture, SA-NCF (Self-Attentive Neural Collaborative Filtering) is a densely connected self-matching model that can be trained up to 24 layers without plateau-ing, achieving wide performance margins against its competitors. On several popular benchmark datasets, our proposed architecture achieves up to an absolute improvement of 23%-58% and 1.3x to 2.8x fold improvement in terms of nDCG@10 and Hit Ratio (HR@10) scores over several strong neural CF baselines.

Value Iteration Networks (VINs) are effective differentiable path planning modules that can be used by agents to perform navigation while still maintaining end-to-end differentiability of the entire architecture. Despite their effectiveness, they suffer from several disadvantages including training instability, random seed sensitivity, and other optimization problems. In this work, we reframe VINs as recurrent-convolutional networks which demonstrates that VINs couple recurrent convolutions with an unconventional max-pooling activation. From this perspective, we argue that standard gated recurrent update equations could potentially alleviate the optimization issues plaguing VIN. The resulting architecture, which we call the Gated Path Planning Network, is shown to empirically outperform VIN on a variety of metrics such as learning speed, hyperparameter sensitivity, iteration count, and even generalization. Furthermore, we show that this performance gap is consistent across different maze transition types, maze sizes and even show success on a challenging 3D environment, where the planner is only provided with first-person RGB images.

But in the last few years, Alexa and Siri have moved in. With this invasion of AI assistants comes incredible command over technology: Don't set a timer or check the weather; ask. And don't spring for that spinning, oak coffee-table caddy to house your obnoxious array of remotes. With the latest TV innovations, all you'll need to say is "Alexa, play'Dawson's Creek'" to immediately power on your TV, streaming device and soundbar, search for the show (now on Hulu), and start where it you left off. "The control and convenience that comes from the next generation of voice is really going to enhance the TV experience," said John Taylor, senior vice president of LG Electronics and friend of Eugene Polley and Dr. Robert Adler, engineers who invented Zenith's original 1950 remote.

At a technology conference in Hannover, Germany, Marc Raibert, the founder of Boston Dynamics, outlined how his company may soon begin to turn its decades-long robotics research into an actual business. Boston Dynamics was sold to SoftBank by Alphabet last year following concerns around its ability to generate revenue. Since the acquisition, it seems that the company has ramped up testing on its increasingly dexterous and nimble robots. Earlier this year, Raibert said the company planned to start selling its SpotMini robot dogs in 2019, and onstage this week, he said the company plans to produce about 100 of the robots by the end of this year. The goal is to begin mass production at the rate of about 1,000 robots per year in the middle of 2019. A slide in Raibert's presentation at CEBIT was titled, "SpotMini Product Platform: 'The Android of Robots'," implying the robots will become the ubiquitous open-source platform for robots that Android has become for smartphones.

Artificial Intelligence Market, the foremost aim of the report is to provide accurate market estimation and to forecast the market on the basis of market segmentation. Significant segments of the market analyzed within the study are technology, end user, and region. The study also provides detailed analysis of top impacting factors and their influence over the market. The report provides the detailed market size with respect to five major regions namely North America, Europe, South America, Asia-Pacific, and Rest of the World. The report contains company profiles of key market leaders and their competitive strategies.

Presenting Fritz Schiltz our youngest speaker of #disummit – he will talk about using #machinelearning to improve the ranking system of schools. Fritz is an applied econometrician at the University of Leuven where he applies advanced analytics to evaluate policies, mainly in education. He has worked on reports for the European Union, the Ministry of Education and Syntra. Halfway his PhD in Economics he shifted his interests towards machine learning methods. His presentation is the result from joint work with the Bank of Italy and illustrates how machine learning or AI methods can be used to improve school rankings using an Italian dataset.

Artificial intelligence (AI) is best known for its ability to see (as in driverless cars) and listen (as in Alexa and other home assistants). My colleagues and I are developing an AI system that can smell human breath and learn how to identify a range of illness-revealing substances that we might breathe out. The sense of smell is used by animals and even plants to identify hundreds of different substances that float in the air. But compared to that of other animals, the human sense of smell is far less developed and certainly not used to carry out daily activities. For this reason, humans aren't particularly aware of the richness of information that can be transmitted through the air, and can be perceived by a highly sensitive olfactory system.

In a recent blog post and tweet, Google announced that it'd be launching a new Artificial Intelligence research centre to be opened later this year in Accra, Ghana. We're continuing to expand our @GoogleAI teams around the world. We'll be opening our first research center in Africa in #Ghana later this year! If you're a machine learning researcher interested in working in Accra, Ghana, apply: https://t.co/YgntDigTJt With this, Accra will be the first African city to join the likes of New York, Montreal, Tokyo, San Francisco, Paris, Beijing, Zurich, Toronto, Seattle, Cambridge/Boston, and Tel Aviv/Haifa, in hosting Google AI centres.

While being a constant learner has its own perks in the industry you're in, it may have long-standing repercussions in the world of AI and automation. When factory workers get automated and replaced for something cheaper and more effective, their skills become inadequate to survive. They then defer to other industries or make other industries more competitive with cheaper labour. That's the true impact of automation that isn't being addressed these days. Research by IT giant Infosys and Future Foundation found that teens living in countries such as India, UK, USA, Australia, France and other leading economies have a significant fear of AI. The youth of these countries believe that their future jobs will be automated in the next 10 years.