In stochastic differential games, a Nash equilibrium refers to strategies by which no player has an incentive to deviate. Finding a Nash equilibrium is one of the core problems in noncooperative game theory, however, due to the notorious intractability of N-player game, the computation of the Nash equilibrium has been shown extremely time-consuming and memory demanding, especially for large N [16]. On the other hand, a rich literature on game theory has been developed to study consequences of strategies on interactions between a large group of rational "agents", e.g., system risk caused by inter-bank borrowing and lending, price impacts imposed by agents' optimal liquidation, and market price from monopolistic competition. This makes it crucial to develop efficient theory and fast algorithms for computing the Nash equilibrium of N-player stochastic differential games. Deep neural networks with many layers have been recently shown to do a great job in artificial intelligence (e.g., [2, 39]). The idea behind is to use compositions of simple functions to approximate complicated ones, and there are approximation theorems showing that a wide class of functions on compact subsets can be approximated by a single hidden layer neural network (e.g., [53]). This brings a possibility of solving a high-dimensional system using deep neural networks, and in fact, these techniques have been successfully applied to solve stochastic control problems [20, 29, 1]. In this paper, we propose to build deep neural networks by using strategies of fictitious play, and develop deep learning algorithms for computing the Nash equilibrium of asymmetric N-player non-zerosum stochastic differential games.

Alzheimer's disease (AD) is the most common neurodegenerative disease in older people. Despite considerable efforts to find a cure for AD, there is a 99.6% failure rate of clinical trials for AD drugs, likely because AD patients cannot easily be identified at early stages. This project investigated machine learning approaches to predict the clinical state of patients in future years to benefit AD research. Clinical data from 1737 patients was obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database and was processed using the "All-Pairs" technique, a novel methodology created for this project involving the comparison of all possible pairs of temporal data points for each patient. This data was then used to train various machine learning models. Models were evaluated using 7-fold cross-validation on the training dataset and confirmed using data from a separate testing dataset (110 patients). A neural network model was effective (mAUC = 0.866) at predicting the progression of AD on a month-by-month basis, both in patients who were initially cognitively normal and in patients suffering from mild cognitive impairment. Such a model could be used to identify patients at early stages of AD and who are therefore good candidates for clinical trials for AD therapeutics.

While Generative Adversarial Networks (GANs) have seen huge successes in image synthesis tasks, they are notoriously difficult to use, in part due to instability during training. One commonly accepted reason for this instability is that gradients passing from the discriminator to the generator can quickly become uninformative, due to a learning imbalance during training. In this work, we propose the Multi-Scale Gradient Generative Adversarial Network (MSG-GAN), a simple but effective technique for addressing this problem which allows the flow of gradients from the discriminator to the generator at multiple scales. This technique provides a stable approach for generating synchronized multi-scale images. We present a very intuitive implementation of the mathematical MSG-GAN framework which uses the concatenation operation in the discriminator computations. We empirically validate the effect of our MSG-GAN approach through experiments on the CIFAR10 and Oxford102 flowers datasets and compare it with other relevant techniques which perform multi-scale image synthesis. In addition, we also provide details of our experiment on CelebA-HQ dataset for synthesizing 1024 x 1024 high resolution images.

Machine learning has been applied to a number of creative, design-oriented tasks. However, it remains unclear how to best empower human users with these machine learning approaches, particularly those users without technical expertise. In this paper we propose a general framework for turn-based interaction between human users and AI agents designed to support human creativity, called {co-creative systems}. The framework can be used to better understand the space of possible designs of co-creative systems and reveal future research directions. We demonstrate how to apply this framework in conjunction with a pair of recent human subject studies, comparing between the four human-AI systems employed in these studies and generating hypotheses towards future studies.

The recommender system is an important form of intelligent application, which assists users to alleviate from information redundancy. Among the metrics used to evaluate a recommender system, the metric of conversion has become more and more important. The majority of existing recommender systems perform poorly on the metric of conversion due to its extremely sparse feedback signal. To tackle this challenge, we propose a deep hierarchical reinforcement learning based recommendation framework, which consists of two components, i.e., high-level agent and low-level agent. The high-level agent catches long-term sparse conversion signals, and automatically sets abstract goals for low-level agent, while the low-level agent follows the abstract goals and interacts with real-time environment. To solve the inherent problem in hierarchical reinforcement learning, we propose a novel deep hierarchical reinforcement learning algorithm via multi-goals abstraction (HRL-MG). Our proposed algorithm contains three characteristics: 1) the high-level agent generates multiple goals to guide the low-level agent in different stages, which reduces the difficulty of approaching high-level goals; 2) different goals share the same state encoder parameters, which increases the update frequency of the high-level agent and thus accelerates the convergence of our proposed algorithm; 3) an appreciate benefit assignment function is designed to allocate rewards in each goal so as to coordinate different goals in a consistent direction. We evaluate our proposed algorithm based on a real-world e-commerce dataset and validate its effectiveness.

Get ready gamers: Google is ready to take on Microsoft, Sony and Nintendo in the gaming space. At the annual Game Developers Conference the technology giant announced its new Stadia gaming platform, looking to make it easier to not just make video games but play them on any screen you own including phones, computers and TVs. Stadia, which will launch later in 2019, promises new ways to connect with games including a Play button on YouTube videos that will launch you from the video into that game. Google demonstrated the new platform at the annual event Tuesday in San Francisco. While showing a video of the game "Assassin's Creed Odyssey," it was shown how a "Play" button on the YouTube video could transport the viewer right into the game.

For most people who talk to our technology -- whether it's Amazon's Alexa, Apple Siri or the Google Assistant -- the voice that talks back sounds female. Some people do choose to hear a male voice. Now, researchers have unveiled a new gender-neutral option: Q. "One of our big goals with Q was to contribute to a global conversation about gender, and about gender and technology and ethics, and how to be inclusive for people that identify in all sorts of different ways," says Julie Carpenter, an expert in human behavior and emerging technologies who worked on developing Project Q. The voice of Q was developed by a team of researchers, sound designers and linguists in conjunction with the organizers of Copenhagen Pride week, technology leaders in an initiative called Equal AI and others. They first recorded dozens of voices of people -- those who identify as male, female, transgender or nonbinary.

Fei-Fei Li heard the crackle of a cat's brain cells a couple of decades ago and has never forgotten it. Researchers had inserted electrodes into the animal's brain and connected them to a loudspeaker, filling a lab at Princeton with the eerie sound of firing neurons. "They played the symphony of a mammalian visual system," she told an audience Monday at Stanford, where she is now a professor. The music of the brain helped convince Li to dedicate herself to studying intelligence--a path that led the physics undergraduate to specializing in artificial intelligence, and helping catalyze the recent flourishing of AI technology and use cases like self-driving cars. These days, though, Li is concerned that the technology she helped bring to prominence may not always make the world better.

Techno-optimist prognosticators will tell you that driverless trucks are just around the corner. They will also gently tell you--always gently--that yes, truck driving, a job that nearly 3.7 million Americans perform today, is perhaps on the brink of extinction. A startup called Peloton Technology sees the future a bit differently. Based in Mountain View, California, the eight-year-old company has a plan to broadly commercialize a partially automated truck technology called platooning. It would still depend on drivers sitting in front of a steering wheel, but it would be more fuel efficient and, hopefully, safer than truck-based transportation today.

Folded and sealed with a dollop of red wax, the will of Catharuçia Savonario Rivoalti lay in Venice's State Archives, unread, for more than six and a half centuries. Scholars don't know why the document, written in 1351, was never opened. But to physicist Fauzia Albertin, the three-page document--six pages, folded--was the perfect thickness for an experiment. Albertin, who now works at the Enrico Fermi Research Center in Italy, wanted to read the will without unsealing it. In a 2017 demonstration, Albertin and her team beamed X-rays at the document to photograph the text inside.