Seoul Special Judicial Police Bureau for Public Safety arrested the CEOs and key players of a cryptocurrency pyramid scheme using the help of AI (Artificial Intelligence) last Thursday. The two main suspects known as Lee and Bae stole a total of 21.2 billion won ($18.3 million in US-Dollars) in a span of 6 months - 12 people were arrested in total. The South Korean police reported the CEOs of this company set up a "members only" shopping website and cryptocurrency exchange in May 2018. The site recruited members for an annual fee of 330,000 won ($288), or a "premium" membership fee of 990,000 won ($864). It also offered 10-year memberships with discounts on hotels, leisures, and on events like weddings and funerals.

Singapore Airlines (SIA) has launched a project to use artificial intelligence and machine learning to predict passengers' consumption patterns in a bid to reduce in-flight food and beverage (F&B) waste. The initiative results from a finalist's idea from last year's SIA AppChallenge, with one of the categories seeking solutions to better track the amount of F&B waste and collect data about passengers' consumption habits to improve efficiency. SIA says that it currently plans meal services based on flight duration and flight timing, but there is still waste on certain flights. The airline relies on customer surveys, data analytics and staff feedback to optimize F&B on board. The airline currently allocates manpower to physically count and record the number of unconsumed meals for certain flights, which is a tedious process.

Police have apprehended a would-be car thief after the Tesla he was attempting to steal alerted its owner to suspicious activity. The electric vehicle's Sentry Mode sent a notification to owner Jed Franklin via the Tesla smartphone app after one of the back windows was broken into while the car was parked in San Francisco. Cameras positioned on the Tesla Model 3 allowed Mr Franklin to record the suspect, both during the incident and in the moments leading up to it. We'll tell you what's true. You can form your own view.

Face recognition is the important field in machine learning and pattern recognition research area. It has a lot of applications in military, finance, public security, to name a few. In this paper, the combination of the tensor sparse PCA with the nearest-neighbor method (and with the kernel ridge regression method) will be proposed and applied to the face dataset. Experimental results show that the combination of the tensor sparse PCA with any classification system does not always reach the best accuracy performance measures. However, the accuracy of the combination of the sparse PCA method and one specific classification system is always better than the accuracy of the combination of the PCA method and one specific classification system and is always better than the accuracy of the classification system itself.

Deep Q-Learning has been successfully applied to a wide variety of tasks in the past several years. However, the architecture of the vanilla Deep Q-Network is not suited to deal with partially observable environments such as 3D video games. For this, recurrent layers have been added to the Deep Q-Network in order to allow it to handle past dependencies. We here use Minecraft for its customization advantages and design two very simple missions that can be frames as Partially Observable Markov Decision Process. We compare on these missions the Deep Q-Network and the Deep Recurrent Q-Network in order to see if the latter, which is trickier and longer to train, is always the best architecture when the agent has to deal with partial observability.

We propose a novel model to address the task of Visual Dialog which exhibits complex dialog structures. To obtain a reasonable answer based on the current question and the dialog history, the underlying semantic dependencies between dialog entities are essential. In this paper, we explicitly formalize this task as inference in a graphical model with partially observed nodes and unknown graph structures (relations in dialog). The given dialog entities are viewed as the observed nodes. The answer to a given question is represented by a node with missing value. We first introduce an Expectation Maximization algorithm to infer both the underlying dialog structures and the missing node values (desired answers). Based on this, we proceed to propose a differentiable graph neural network (GNN) solution that approximates this process. Experiment results on the VisDial and VisDial-Q datasets show that our model outperforms comparative methods. It is also observed that our method can infer the underlying dialog structure for better dialog reasoning.

Dialog is an effective way to exchange information, but subtle details and nuances are extremely important. While significant progress has paved a path to address visual dialog with algorithms, details and nuances remain a challenge. Attention mechanisms have demonstrated compelling results to extract details in visual question answering and also provide a convincing framework for visual dialog due to their interpretability and effectiveness. However, the many data utilities that accompany visual dialog challenge existing attention techniques. We address this issue and develop a general attention mechanism for visual dialog which operates on any number of data utilities. To this end, we design a factor graph based attention mechanism which combines any number of utility representations. We illustrate the applicability of the proposed approach on the challenging and recently introduced VisDial datasets, outperforming recent state-of-the-art methods by 1.1% for VisDial0.9 and by 2% for VisDial1.0 on MRR. Our ensemble model improved the MRR score on VisDial1.0 by more than 6%.

This paper addresses the problem of unsupervised domain adaption from theoretical and algorithmic perspectives. Existing domain adaptation theories naturally imply minimax optimization algorithms, which connect well with the adversarial-learning based domain adaptation methods. However, several disconnections still form the gap between theory and algorithm. We extend previous theories (Ben-David et al., 2010; Mansour et al., 2009c) to multiclass classification in domain adaptation, where classifiers based on scoring functions and margin loss are standard algorithmic choices. We introduce a novel measurement, margin disparity discrepancy, that is tailored both to distribution comparison with asymmetric margin loss, and to minimax optimization for easier training. Using this discrepancy, we derive new generalization bounds in terms of Rademacher complexity. Our theory can be seamlessly transformed into an adversarial learning algorithm for domain adaptation, successfully bridging the gap between theory and algorithm. A series of empirical studies show that our algorithm achieves the state-of-the-art accuracies on challenging domain adaptation tasks.

In this paper we study how different ways of combining character and word-level representations affect the quality of both final word and sentence representations. We provide strong empirical evidence that modeling characters improves the learned representations at the word and sentence levels, and that doing so is particularly useful when representing less frequent words. We further show that a feature-wise sigmoid gating mechanism is a robust method for creating representations that encode semantic similarity, as it performed reasonably well in several word similarity datasets. Finally, our findings suggest that properly capturing semantic similarity at the word level does not consistently yield improved performance in downstream sentence-level tasks. Our code is available at https://github.com/jabalazs/gating

In MIT Technology Review, Jeff Ding shares five takeaways from his experience writing about and translating Chinese-language writing about artificial intelligence (AI) research in China. Ding is a researcher at the University of Oxford who has now published 48 issues of his insightful ChinAI newsletter. Four out of Ding's five points are likely to remain true through at least 2019. The odd one out is number four: AI research, in the near future, may no longer be an area of active China-U.S. collaboration. For more discussion of U.S.-China technology connections, listen to this recent Sinica Podcast with Samm Sacks.