Recent advances in Neural Variational Inference allowed for a renaissance in latent variable models in a variety of domains involving high-dimensional data. While traditional variational methods derive an analytical approximation for the intractable distribution over the latent variables, here we construct an inference network conditioned on the symbolic representation of entities and relation types in the Knowledge Graph, to provide the variational distributions. The new framework results in a highly-scalable method. Under a Bernoulli sampling framework, we provide an alternative justification for commonly used techniques in large-scale stochastic variational inference, which drastically reduce training time at a cost of an additional approximation to the variational lower bound. We introduce two models from this highly scalable probabilistic framework, namely the Latent Information and Latent Fact models, for reasoning over knowledge graph-based representations. Our Latent Information and Latent Fact models improve upon baseline performance under certain conditions. We use the learnt embedding variance to estimate predictive uncertainty during link prediction, and discuss the quality of these learnt uncertainty estimates. Our source code and datasets are publicly available online at https://github.com/alexanderimanicowenrivers/Neural-Variational-Knowledge-Graphs.

Obtaining training data for Question Answering (QA) is time-consuming and resource-intensive, and existing QA datasets are only available for limited domains and languages. In this work, we explore to what extent high quality training data is actually required for Extractive QA, and investigate the possibility of unsupervised Extractive QA. We approach this problem by first learning to generate context, question and answer triples in an unsupervised manner, which we then use to synthesize Extractive QA training data automatically. To generate such triples, we first sample random context paragraphs from a large corpus of documents and then random noun phrases or named entity mentions from these paragraphs as answers. Next we convert answers in context to "fill-in-the-blank" cloze questions and finally translate them into natural questions. We propose and compare various unsupervised ways to perform cloze-to-natural question translation, including training an unsupervised NMT model using non-aligned corpora of natural questions and cloze questions as well as a rule-based approach. We find that modern QA models can learn to answer human questions surprisingly well using only synthetic training data. We demonstrate that, without using the SQuAD training data at all, our approach achieves 56.4 F1 on SQuAD v1 (64.5 F1 when the answer is a Named entity mention), outperforming early supervised models.

We propose an efficient neural framework for sentence-level discourse analysis in accordance with Rhetorical Structure Theory (RST). Our framework comprises a discourse segmenter to identify the elementary discourse units (EDU) in a text, and a discourse parser that constructs a discourse tree in a top-down fashion. Both the segmenter and the parser are based on Pointer Networks and operate in linear time. Our segmenter yields an $F_1$ score of 95.4, and our parser achieves an $F_1$ score of 81.7 on the aggregated labeled (relation) metric, surpassing previous approaches by a good margin and approaching human agreement on both tasks (98.3 and 83.0 $F_1$).

Brain scans on fanatical Islamists show they have a reduced capacity for rational thought, new research suggests. Members of a radical Islamist group were asked how willing they were to'fight and die' for their ideas. Their brains were then scanned during the process. The results showed that when questioned, the part of the brain that engages in evaluating costs and consequences showed reduced activity. The scientists say this shows that when it comes to values held'sacred' to the radicals, they are immune to arguments involving costs and benefits.

Dr. Tambe describes his team's use of security games to combat poaching, and his experience deploying his algorithms to inform park ranger schedules internationally. Dr. Milind Tambe is the Helen N. and Emmett H. Jones Professor in Engineering at the University of Southern California, and Professor in the Computer Science and Industrial and Systems Engineering Departments. He is a founding co-director of the CAIS Center for AI in Society, where he advises students and conducts research on multiagent teamwork, distributed constraint optimization, and security games. The security games framework developed by Dr. Tambe has been deployed and tested nationally and internationally, and led to his co-founding of company Avata Intelligence.

Mario's brother Luigi is the ghostbusting star in'Luigi's Mansion 3,' a new video game coming to Nintendo Switch later this year. LOS ANGELES – Mario is usually front and center for Nintendo, but the video game maker has propelled his brother Luigi to the forefront at this year's Electronic Entertainment Expo. The upcoming game "Luigi's Mansion 3," out later this year for Nintendo Switch, got headlining treatment during the Nintendo Direct online video message Tuesday, just before the doors opened at the E3 expo, which runs through Thursday. The setup: A scary adventure ensues after what Luigi and Mario thought was going to be a fun vacation getaway at an upscale resort, instead turns out to be a trip to haunted hotel. When Mario and Princess Peach go missing, Luigi must become a ghostbuster and find them.

The wait is over as gamers get a glimpse of Activision's 2019 "Call of Duty: Modern Warfare." LOS ANGELES – We already knew that the next "Call of Duty" video game would reclaim the "Modern Warfare" brand. But the Activision-owned studio Infinity Ward revealed new details about the game here at the Electronic Entertainment Expo, showing some footage from the game and talking about its development. Set in the modern day, "Call of Duty: Modern Warfare," out Oct. 25 for PS4, Xbox One and PCs, will pit U.S. and allied troops, including freedom fighters, against an international threat. The game is not a sequel to the trilogy of releases from Infinity Ward that started with 2007's "Call of Duty 4: Modern Warfare" and ended with "Call of Duty: Modern Warfare 3" in 2011.

Researchers at the Samsung AI Center in Moscow, Russia have quite amazingly turned Mona Lisa and other famous subjects of photos and art into realistic talking heads. When an image is presented, the matching landmark features are located and put to work. Such examples include The Mona Lisa, Albert Einstein, and Salvador Dali. The results are spooky, to say the least. We present a system for learning full-body neural avatars, i.e. deep networks that produce full-body renderings of a person for varying body pose and camera position.

One of my favorite things about deep reinforcement learning is that, unlike supervised learning, it really, really doesn't want to work. Throwing a neural net at a computer vision problem might get you 80% of the way there. Throwing a neural net at an RL problem will probably blow something up in front of your face -- and it will blow up in a different way each time you try. A lot of the biggest challenges in RL revolve around two questions: how we interact with the environment effectively (e.g. In this post, I want to explore a few recent directions in deep RL research that attempt to address these challenges, and do so with particularly elegant parallels to human cognition. This post will begin with a quick review of two canonical deep RL algorithms -- DQN and A3C -- to provide us some intuitions to refer back to, and then jump into a deep dive on a few recent papers and breakthroughs in the categories described above.

Few companies had enjoyed the sort of bull run AI chipmaker Nvidia (NVDA) had been on, returning more than 1200% between June 2015 and June 2018, eventually hitting a market cap of about $175 billion by September 2018. Then everything went south – literally – as the market took a historic plunge in the fourth quarter, taking Nvidia with it. However, while many companies have bounced back, Nvidia has continued to languish, sitting at a valuation of about $88 billion, pretty much where it was circa May 2017 when we compared its AI chip technology against AMD (AMD). Now, over the last five years, the two chip manufacturers have returned almost identical value to investors, while a number of upstart startups have risen to also challenge Nvidia's supremacy with new artificial intelligence chips. In fact, it was exactly three years ago that we first introduced you to five startups building artificial intelligence chips, and then followed that up with 12 new AI chip makers in 2017.