Generative Adversarial Networks (GAN) (Goodfellow et al., 2014) are one of the most prominent tools for learning complicated distributions. However, problems such as mode collapse and catastrophic forgetting, prevent GAN from learning the target distribution. These problems are usually studied independently from each other. In this paper, we show that both problems are present in GAN and their combined effect makes the training of GAN unstable. We also show that methods such as gradient penalties and momentum based optimizers can improve the stability of GAN by effectively preventing these problems from happening. Finally, we study a mechanism for mode collapse to occur and propagate in feedforward neural networks.

While several feature scoring methods are proposed to explain the output of complex machine learning models, most of them lack formal mathematical definitions. In this study, we propose a novel definition of the feature score using the maximally invariant data perturbation, which is inspired from the idea of adversarial example. In adversarial example, one seeks the smallest data perturbation that changes the model's output. In our proposed approach, we consider the opposite: we seek the maximally invariant data perturbation that does not change the model's output. In this way, we can identify important input features as the ones with small allowable data perturbations. To find the maximally invariant data perturbation, we formulate the problem as linear programming. The experiment on the image classification with VGG16 shows that the proposed method could identify relevant parts of the images effectively.

Missing data are ubiquitous in many domains such as healthcare. Depending on how they are missing, the (conditional) independence relations in the observed data may be different from those for the complete data generated by the underlying causal process and, as a consequence, simply applying existing causal discovery methods to the observed data may lead to wrong conclusions. It is then essential to extend existing causal discovery approaches to find true underlying causal structure from such incomplete data. In this paper, we aim at solving this problem for data that are missing with different mechanisms, including missing completely at random (MCAR), missing at random (MAR), and missing not at random (MNAR). With missingness mechanisms represented by missingness Graph (m-Graph), we analyze conditions under which addition correction is needed to derive conditional independence/dependence relations in the complete data. Based on our analysis, we propose missing value PC (MVPC), which combines additional corrections with traditional causal discovery algorithm, in particular, PC. Our proposed MVPC is shown in theory to give asymptotically correct results even using data that are MAR and MNAR. Experiment results illustrate that the proposed algorithm can correct the conditional independence for values MCAR, MAR and rather general cases of values MNAR both with synthetic data as well as real-life healthcare application.

Due to the iterative nature of most nonnegative matrix factorization (\textsc{NMF}) algorithms, initialization is a key aspect as it significantly influences both the convergence and the final solution obtained. Many initialization schemes have been proposed for NMF, among which one of the most popular class of methods are based on the singular value decomposition (SVD). However, these SVD-based initializations do not satisfy a rather natural condition, namely that the error should decrease as the rank of factorization increases. In this paper, we propose a novel SVD-based \textsc{NMF} initialization to specifically address this shortcoming by taking into account the SVD factors that were discarded to obtain a nonnegative initialization. This method, referred to as nonnegative SVD with low-rank correction (NNSVD-LRC), allows us to significantly reduce the initial error at a negligible additional computational cost using the low-rank structure of the discarded SVD factors. NNSVD-LRC has two other advantages compared to previous SVD-based initializations: (1) it provably generates sparse initial factors, and (2) it is faster as it only requires to compute a truncated SVD of rank $\lceil r/2 + 1 \rceil$ where $r$ is the factorization rank of the sought NMF decomposition (as opposed to a rank-$r$ truncated SVD for other methods). We show on several standard dense and sparse data sets that our new method competes favorably with state-of-the-art SVD-based initializations for NMF.

Due to recent explosion of text data, researchers have been overwhelmed by ever-increasing volume of articles produced by different research communities. Various scholarly search websites, citation recommendation engines, and research databases have been created to simplify the text search tasks. However, it is still difficult for researchers to be able to identify potential research topics without doing intensive reviews on a tremendous number of articles published by journals, conferences, meetings, and workshops. In this paper, we consider a novel topic diffusion discovery technique that incorporates sparseness-constrained Non-negative Matrix Factorization with generalized Jensen-Shannon divergence to help understand term-topic evolutions and identify topic diffusions. Our experimental result shows that this approach can extract more prominent topics from large article databases, visualize relationships between terms of interest and abstract topics, and further help researchers understand whether given terms/topics have been widely explored or whether new topics are emerging from literature.

Like in a Tough Mudder, you've got a few strategies when it comes to the race to launch a taxi-like service with autonomous vehicles. You can start early and keep a slow but steady pace. You can show up a bit late, then try to sprint through it. Or you can hold back, see what trips up other contenders, and then slowly work your way through the obstacles. The big automakers tend to fall into the third category. They may have taken a few years to recognize that shared autonomous vehicles could annihilate their business model--selling human-driven cars to individual humans--but they're now making real progress toward the finish line.

LONDON – Most people think the world is more dangerous today than it was two years ago as concerns rise over politically motivated violence and weapons of mass destruction, according to a survey released on Tuesday. Six out of 10 respondents to the survey, commissioned by the Global Challenges Foundation, said the dangers had increased, with conflict and nuclear or chemical weapons seen as more pressing risks than population growth or climate change. The results come as NATO leaders prepare to meet in Brussels on Wednesday amid growing tensions between the United States and fellow members over defense spending, which some fear could damage morale and play into the hands of Russia. "It's clear that our current systems of global cooperation are no longer making people feel safe," said Mats Andersson, vice chairman of the Global Challenges Foundation, in a statement. Andersson said turbulence between NATO powers and Russia, ongoing conflict in Syria, Yemen and Ukraine and nuclear tensions with North Korea and Iran were making people feel unsafe.

WASHINGTON--(BUSINESS WIRE)--The following is an opinion editorial provided by Naveen Rao of Intel Corporation. Most people agree that artificial intelligence (AI) will transform modern society in positive ways. From autonomous cars that will save thousands of lives, to data analytics programs that may finally discover a cure for cancer, to machines that give voice to those who can't speak, AI will be known as one of the most revolutionary innovations of mankind. But this fantastic future is a long way off, and the path to get us there is still under construction. Never before has society undertaken such a significant transformation so deliberately, and no blueprints exist to guide us.

Psychology and neuroscience have played a key role in the history of AI and this is central to Starmind's activities. The new desktop app consolidates and improves upon Starmind's features, allowing ease of access without a web portal, pop-up notifications when an expert answers a question, and a more seamless UI. Starmind facilitates collaboration throughout large companies by using AI to learn who in a given company is an expert on a given topic, then matching employees with questions/problems to the relevant experts. To understand the basics of neuroscientific artificial intelligence and the Starmind application, Digital Journal caught up with Peter Wasser, the company's CEO. Digital Journal: How important is artificial intelligence to the modern company?

Audi plans to make five new-energy vehicle models in China by 2022, the company's China head Joachim Wedler said today. Autonomous Intelligent Driving (AID) is a wholly owned subsidiary of Audi AG with a fleet of test vehicles that are running an autonomous vehicle simulation platform from Cognata, an Israeli artificial intelligence (AI) and deep learning company. Their platform uses AI, deep learning and computer vision in a realistic and safe simulation environment to simulate and validate autonomous vehicles prior vehicles moving to test phases on real roads. "Previously autonomous vehicles were a hyped AI experiment and companies were at the stage of trying out prototypes on the road. Autonomous vehicles have now evolved into a more mature product that demands human-like performance, which means zero tolerance for safety issues and efficiency in a high traffic environment," said Danny Atsmon, CEO, Cognata.