The Expectation Maximization (EM) algorithm is the default algorithm for inference in latent variable models. As in any other field of machine learning, applications of latent variable models to very large datasets makes the use of advanced parallel and distributed architectures mandatory. This paper introduces FedEM, which is the first extension of the EM algorithm to the federated learning context. FedEM is a new communication efficient method, which handles partial participation of local devices, and is robust to heterogeneous distributions of the datasets. To alleviate the communication bottleneck, FedEM compresses appropriately defined complete data sufficient statistics. We also develop and analyze an extension of FedEM to further incorporate a variance reduction scheme. In all cases, we derive finite-time complexity bounds for smooth non-convex problems. Numerical results are presented to support our theoretical findings, as well as an application to federated missing values imputation for biodiversity monitoring.

Does your pooch look like a Picasso or your gerbil a Gauguin? Well, you can find out thanks to a Google feature that reveals which famous artwork your pet resembles. Part of the Google Arts & Culture app, Pet Portraits uses machine learning algorithms to scan a photo of your pet and find the best matches from hundreds of years of art. The system works with various animals including cats, dogs birds, fish, horses, rabbits and reptiles, and is available on Android and iOS. It builds upon the success of Art Selfie, a similar feature launched in 2018 that let us humans find our eerie doppelgängers from the world of fine art.

Peloton's fitness ambitions go far beyond treadmills and stationary bikes. Its next product is the Peloton Guide, a strength-training camera system that hooks up to your TV and uses machine learning to understand your movements. The movement tracker feature is compatible with hundreds of Peloton strength classes. The idea is to encourage users to carry out all of the exercises in a class and keep up with instructors (but it's not a big deal if you can't stick to the instructor's pace). The Self Mode will enable users to match their form against the instructor's in real-time via smart camera technology.

Peloton has announced the'Guide', its first connected strength product. The Guide is something like a camera with artificial intelligence built in. It plugs into a TV and is then able to watch how people work out, giving them guidance on their form and what workouts they should be doing. To use it, the Guide is plugged into the TV and people can then use their existing equipment and weights. The camera then uses machine learning to track users' movements, ensuring users are completing the exercises and allowing them to watch their own performance, as well as showing which muscle groups have recently been worked and which should be in the future.

Netflix will roll out a new TikTok-inspired featured that specifically targets its younger viewers this week, according to Bloomberg. The streaming giant is reportedly launching "Kids Clips" on its iOS app, which will show short video clips from its library of children's programming to help young viewers find something to watch. Bloomberg says the feature builds upon Fast Laughs, the comedy feed it launched earlier this year. Unlike Fast Laughs, however, Kids Clips videos will be horizontal instead of vertical and will take over the entire screen. In addition, kids will only be able to view 10 to 20 clips at any one time.

This study proposes a novel method to assess damages in the built environment using a deep learning workflow to quantify it. Thanks to an automated crawler, aerial images from before and after a natural disaster of 50 epicenters worldwide were obtained from Google Earth, generating a 10,000 aerial image database with a spatial resolution of 2 m per pixel. The study utilizes the algorithm Seg-Net to perform semantic segmentation of the built environment from the satellite images in both instances (prior and post-natural disasters). For image segmentation, Seg-Net is one of the most popular and general CNN architectures. The Seg-Net algorithm used reached an accuracy of 92% in the segmentation. After the segmentation, we compared the disparity between both cases represented as a percentage of change. Such coefficient of change represents the damage numerically an urban environment had to quantify the overall damage in the built environment. Such an index can give the government an estimate of the number of affected households and perhaps the extent of housing damage.

International collaboration has become imperative in the field of AI. However, few studies exist concerning how distance factors have affected the international collaboration in AI research. In this study, we investigate this problem by using 1,294,644 AI related collaborative papers harvested from the Microsoft Academic Graph (MAG) dataset. A framework including 13 indicators to quantify the distance factors between countries from 5 perspectives (i.e., geographic distance, economic distance, cultural distance, academic distance, and industrial distance) is proposed. The relationships were conducted by the methods of descriptive analysis and regression analysis. The results show that international collaboration in the field of AI today is not prevalent (only 15.7%). All the separations in international collaborations have increased over years, except for the cultural distance in masculinity/felinity dimension and the industrial distance. The geographic distance, economic distance and academic distances have shown significantly negative relationships with the degree of international collaborations in the field of AI. The industrial distance has a significant positive relationship with the degree of international collaboration in the field of AI. Also, the results demonstrate that the participation of the United States and China have promoted the international collaboration in the field of AI. This study provides a comprehensive understanding of internationalizing AI research in geographic, economic, cultural, academic, and industrial aspects.

Despite advances in hierarchical reinforcement learning, its applications to path planning in autonomous driving on highways are challenging. One reason is that conventional hierarchical reinforcement learning approaches are not amenable to autonomous driving due to its riskiness: the agent must move avoiding multiple obstacles such as other agents that are highly unpredictable, thus safe regions are small, scattered, and changeable over time. To overcome this challenge, we propose a spatially hierarchical reinforcement learning method for state space and policy space. The high-level policy selects not only behavioral sub-policy but also regions to pay mind to in state space and for outline in policy space. Subsequently, the low-level policy elaborates the short-term goal position of the agent within the outline of the region selected by the high-level command. The network structure and optimization suggested in our method are as concise as those of single-level methods. Experiments on the environment with various shapes of roads showed that our method finds the nearly optimal policies from early episodes, outperforming a baseline hierarchical reinforcement learning method, especially in narrow and complex roads. The resulting trajectories on the roads were similar to those of human strategies on the behavioral planning level.

Large language models can produce fluent dialogue but often hallucinate factual inaccuracies. While retrieval-augmented models help alleviate this issue, they still face a difficult challenge of both reasoning to provide correct knowledge and generating conversation simultaneously. In this work, we propose a modular model, Knowledge to Response (K2R), for incorporating knowledge into conversational agents, which breaks down this problem into two easier steps. K2R first generates a knowledge sequence, given a dialogue context, as an intermediate step. After this "reasoning step", the model then attends to its own generated knowledge sequence, as well as the dialogue context, to produce a final response. In detailed experiments, we find that such a model hallucinates less in knowledge-grounded dialogue tasks, and has advantages in terms of interpretability and modularity. In particular, it can be used to fuse QA and dialogue systems together to enable dialogue agents to give knowledgeable answers, or QA models to give conversational responses in a zero-shot setting.

Deep learning-based detection networks have made remarkable progress in autonomous driving systems (ADS). ADS should have reliable performance across a variety of ambient lighting and adverse weather conditions. However, luminance degradation and visual obstructions (such as glare, fog) result in poor quality images by the visual camera which leads to performance decline. To overcome these challenges, we explore the idea of leveraging a different data modality that is disparate yet complementary to the visual data. We propose a comprehensive detection system based on a multimodal-collaborative framework that learns from both RGB (from visual cameras) and thermal (from Infrared cameras) data. This framework trains two networks collaboratively and provides flexibility in learning optimal features of its own modality while also incorporating the complementary knowledge of the other. Our extensive empirical results show that while the improvement in accuracy is nominal, the value lies in challenging and extremely difficult edge cases which is crucial in safety-critical applications such as AD. We provide a holistic view of both merits and limitations of using a thermal imaging system in detection.