Through collecting a massively large number of tweets and building machine learning models, we investigate the dynamics of the Twitter social network formed by the interactions among millions of Twitter supporters. Our predictions are updated daily at 2AM.

When Arnold Schwarzenegger's "Terminator" character said "I'll be back," this probably wasn't what he had in mind. The actor and former governor of California is suing a robotics company for $10 million, after the business decided to use his name and likeness. Schwarzenegger's lawsuit against the tech startup, called Promobot, alleges that the robot lookalike... "diminishes his hard-earned and well-deserved reputation as a major motion picture star," according to TMZ. The robot isn't just meant to look like Schwarzenegger, it also has his name. Promobot advertises the creation on its site as a "companion robot," one of several that emulates the appearance of world-famous celebrities.

Artificial intelligence (AI) is no longer the stuff of science fiction. While robot maids may not yet be a reality, researchers are working hard to create reasoning, problem-solving machines whose "brains" might rival our own. Seán Ó hÉigeartaigh (anglicized as Sean O'Hegarty), while enthusiastic about the benefits that AI can bring, is also wary of the technology's dark side. He holds a doctorate in genomics from Trinity College Dublin and is now executive director of the Center for the Study of Existential Risk at the University of Cambridge. He has played a central role in international research on the long-term impacts and risks of AI.

Sign in to report inappropriate content. The rapid industrialization of Indonesia has taken a toll on its 297 km long Citarum River, which is now one of the world's most polluted rivers. Locals and environmentalists are now accessing digital solutions to measure, monitor, and support the river's clean up. One of these solutions is a tree management system developed by Danone-AQUA and Microsoft partner, Jejak.in that uses IoT and AI technologies to collect and analyze ecological data.

Machine Learning is evidently a vast field and its study is one of the most enlightening tasks one could ever undertake. Today most of the business operations and innovations are done around ML and its innovative applications. A number of professionals are up-skilling themselves with advanced ML knowledge to thrive ahead in their respective fields. They are more keen on learning the offerings, advancements, experts' opinion and various nuances in context to machine learning or artificial intelligence (AI) as a whole. If you are tech-enthusiast and looking forward to learning some new ideas and innovations about machine learning, you can find plenty of comprehensive books that demonstrate and offer various skills, advice and learning opportunities.

Sure, multiplayer-heavy video games, like Fortnite and Call of Duty, tend to monopolize the buzz and attention. But the past few months and years have given us some truly incredible solo experiences, too, like Stardew Valley and Red Dead Redemption 2. If you're getting bored of competitive online gaming, or that's not your cup of tea in the first place, you have plenty of great single-player games to choose from these days. Which games should you get if you're looking to go offline for a while and enjoy some solo time on the couch or during your commute? God of War, Spider-Man, Horizon: Zero Dawn, and Uncharted 4: A Thief's End are all incredible single-player games on the PlayStation 4. Spider-Man and Horizon: Zero Dawn are open-world action games with large maps and dozens of activities to choose from. Uncharted 4 is like an interactive movie, while God of War is a father-son adventure story that trades in the series' trademark button-mashing action for slow, considered, and careful combat.

Deep networks have enabled significant performance gains across domains, but they often suffer from vanishing/exploding gradients. This is especially true for Transformer architectures where depth beyond 12 layers is difficult to train without large datasets and computational budgets. In general, we find that inefficient signal propagation impedes learning in deep networks. In Transformers, multi-head self-attention is the main cause of this poor signal propagation. To facilitate deep signal propagation, we propose ReZero, a simple change to the architecture that initializes an arbitrary layer as the identity map, using a single additional learned parameter per layer. We apply this technique to language modeling and find that we can easily train ReZero-Transformer networks over a hundred layers. When applied to 12 layer Transformers, ReZero converges 56% faster on enwiki8. ReZero applies beyond Transformers to other residual networks, enabling 1,500% faster convergence for deep fully connected networks and 32% faster convergence for a ResNet-56 trained on CIFAR 10.

Entity alignment seeks to find entities in different knowledge graphs (KGs) that refer to the same real-world object. Recent advancement in KG embedding impels the advent of embedding-based entity alignment, which encodes entities in a continuous embedding space and measures entity similarities based on the learned embeddings. In this paper, we conduct a comprehensive experimental study of this emerging field. This study surveys 23 recent embedding-based entity alignment approaches and categorizes them based on their techniques and characteristics. We further observe that current approaches use different datasets in evaluation, and the degree distributions of entities in these datasets are inconsistent with real KGs. Hence, we propose a new KG sampling algorithm, with which we generate a set of dedicated benchmark datasets with various heterogeneity and distributions for a realistic evaluation. This study also produces an open-source library, which includes 12 representative embedding-based entity alignment approaches. We extensively evaluate these approaches on the generated datasets, to understand their strengths and limitations. Additionally, for several directions that have not been explored in current approaches, we perform exploratory experiments and report our preliminary findings for future studies. The benchmark datasets, open-source library and experimental results are all accessible online and will be duly maintained.

Ranking alternatives is a natural way for humans to explain their preferences. It is used in many settings, such as school choice, course allocations and residency matches. Without having any information on the underlying cardinal utilities, arguing about the fairness of allocations requires extending the ordinal item ranking to ordinal bundle ranking. The most commonly used such extension is stochastic dominance (SD), where a bundle X is preferred over a bundle Y if its score is better according to all additive score functions. SD is a very conservative extension, by which few allocations are necessarily fair while many allocations are possibly fair. We propose to make a natural assumption on the underlying cardinal utilities of the players, namely that the difference between two items at the top is larger than the difference between two items at the bottom. This assumption implies a preference extension which we call diminishing differences (DD), where X is preferred over Y if its score is better according to all additive score functions satisfying the DD assumption. We give a full characterization of allocations that are necessarily-proportional or possibly-proportional according to this assumption. Based on this characterization, we present a polynomial-time algorithm for finding a necessarily-DD-proportional allocation whenever it exists. Using simulations, we compare the various fairness criteria in terms of their probability of existence, and their probability of being fair by the underlying cardinal valuations. We find that necessary-DD-proportionality fares well in both measures. We also consider envy-freeness and Pareto optimality under diminishing-differences, as well as chore allocation under the analogous condition --- increasing-differences.

We propose a nested reduced-rank regression (NRRR) approach in fitting regression model with multivariate functional responses and predictors, to achieve tailored dimension reduction and facilitate interpretation/visualization of the resulting functional model. Our approach is based on a two-level low-rank structure imposed on the functional regression surfaces. A global low-rank structure identifies a small set of latent principal functional responses and predictors that drives the underlying regression association. A local low-rank structure then controls the complexity and smoothness of the association between the principal functional responses and predictors. Through a basis expansion approach, the functional problem boils down to an interesting integrated matrix approximation task, where the blocks or submatrices of an integrated low-rank matrix share some common row space and/or column space. An iterative algorithm with convergence guarantee is developed. We establish the consistency of NRRR and also show through non-asymptotic analysis that it can achieve at least a comparable error rate to that of the reduced-rank regression. Simulation studies demonstrate the effectiveness of NRRR. We apply NRRR in an electricity demand problem, to relate the trajectories of the daily electricity consumption with those of the daily temperatures.