In this paper, we consider the problem of recovering a graph that represents the statistical data dependency among nodes for a set of data samples generated by nodes, which provides the basic structure to perform an inference task, such as MAP (maximum a posteriori). This problem is referred to as structure learning. When nodes are spatially separated in different locations, running an inference algorithm requires a non-negligible amount of message passing, incurring some communication cost. We inevitably have the trade-off between the accuracy of structure learning and the cost we need to pay to perform a given message-passing based inference task because the learnt edge structures of data dependency and physical connectivity graph are often highly different. In this paper, we formalize this trade-off in an optimization problem which outputs the data dependency graph that jointly considers learning accuracy and message-passing costs. We focus on a distributed MAP as the target inference task, and consider two different implementations, ASYNC-MAP and SYNC-MAP that have different message-passing mechanisms and thus different cost structures. In ASYNC- MAP, we propose a polynomial time learning algorithm that is optimal, motivated by the problem of finding a maximum weight spanning tree. In SYNC-MAP, we first prove that it is NP-hard and propose a greedy heuristic. For both implementations, we then quantify how the probability that the resulting data graphs from those learning algorithms differ from the ideal data graph decays as the number of data samples grows, using the large deviation principle, where the decaying rate is characterized by some topological structures of both original data dependency and physical connectivity graphs as well as the degree of the trade-off. We validate our theoretical findings through extensive simulations, which confirms that it has a good match.

Recent research has shown that deep ensemble for forest can achieve a huge increase in classification accuracy compared with the general ensemble learning method. Especially when there are only few training data. In this paper, we decide to take full advantage of this observation and introduce the Dense Adaptive Cascade Forest (daForest), which has better performance than the original one named Cascade Forest. And it is particularly noteworthy that daForest has a powerful ability to handle high-dimensional sparse data without any preprocessing on raw data like PCA or any other dimensional reduction methods. Our model is distinguished by three major features: the first feature is the combination of the SAMME.R boosting algorithm in the model, boosting gives the model the ability to continuously improve as the number of layer increases, which is not possible in stacking model or plain cascade forest. The second feature is our model connects each layer to its subsequent layers in a feed-forward fashion, to some extent this structure enhances the ability of the model to resist degeneration. When number of layers goes up, accuracy of model goes up a little in the first few layers then drop down quickly, we call this phenomenon degeneration in training stacking model. The third feature is that we add a hyper-parameter optimization layer before the first classification layer in the proposed deep model, which can search for the optimal hyper-parameter and set up the model in a brief period and nearly halve the training time without having too much impact on the final performance. Experimental results show that daForest performs particularly well on both high-dimensional low-order features and low-dimensional high-order features, and in some cases, even better than neural networks and achieves state-of-the-art results.

Facial recognition technology is really starting to become a big deal in China. It wasn't that long ago when Chinese traffic police began using facial recognition to nab those who were violating traffic laws. Now they've taken things one step further with artificial intelligence (AI): When the facial recognition cameras catch someone jaywalking, not only will they be identified, named, and publicly shamed, they will also be sent text messages telling them what their violation is and how much the fine they have to pay will be. Based on online reports, a Shenzhen-based AI company called Intellifusion will be in charge of rolling out this "feature" of the new Shenzhen traffic system. That is, in addition to simply displaying the faces of jaywalkers on giant LED screens located at intersections, they will be working with local mobile phone carriers and social media companies in order to work out a system that will send out the jaywalking-related text messages to jaywalkers as soon as they get caught. And things can only get worse for traffic violators.

Lin Ma is a Principal Researcher at Tencent AI Lab based in Shenzhen, China. His current research interests lie in the areas of computer vision and deep learning, such as image/video processing, analysis, and understanding. Previously, he was a Researcher with Huawei Noah's Ark Lab, Hong Kong. Lin Ma received his Ph.D. degree in Department of Electronic Engineering at the Chinese University of Hong Kong (CUHK) in 2013. He received the B. E., and M. E. degrees from Harbin Institute of Technology, Harbin, China, in 2006 and 2008, respectively, both in computer science.

Roundup Here's your roundup of machine-learning news from this week, beyond what we've already covered. Axon AI Ethics board A group of civil rights groups and technology researchers has written a letter to Axon, a company that uses AI to analyze video footage aimed at law enforcement. Axon recently announced it had set up an AI ethics board to guide its products and services. In response, the letter urges the company to not develop real-time facial recognition for police body cameras to prevent misidentifying civilians as criminals, to ethically reviewing all its other products, and to reach out to "survivors of law enforcement harm and violence" for advice. You can read the letter here.

A video game has been made about the conflict in Syria.

Facial recognition technology is penetrating deep into China. Cameras track passengers at railway stations, identify homeless people on the streets, and even monitor worshippers in state-approved churches. China's nation-wide surveillance project, named Skynet, began as early as 2005. But recent advances in artificial intelligence have given the state's surveillance efforts a boost. Join us for a live briefing as we dive into the Chinese government's AI strategy, what tech giants like Alibaba and Tencent are doing in AI, startup activity, and China's cross-border AI initiatives.

A new study exploring depths of the Gulf of Oman revealed a massive increase in the size of its "dead zone," an area with too little oxygen for the survival of marine life. First spotted nearly half a century ago, dead-zones, aka oxygen minimum zones or OMZs, were flagged as a major threat to marine biology. They occur naturally at depths ranging from 700 to 2500 feet due to changes in the level of atmospheric oxygen and have been located in three to four parts of the world including the Gulf of Oman which shares its waters with the Arabian Sea. Now, that dead-zone appears to have grown bigger than what was previously thought. During a recent study, scientists from the University of East Anglia (UEA) sent two underwater robots, dubbed Seagliders, into the gulf to create a detailed picture of oxygen levels and the mechanics that mix oxygen and other nutrients into the water.

IIIT Hyderabad on Thursday announced the success of the first cycle of its Foundations of Artificial Intelligence and Machine Learning (AI/ML) programme, conducted by its Machine Learning Lab in association with TalentSprint.

Noted Indian scientists from the National Brain Research Centre (NBRC), and Neuroimaging and Neurospectroscopy Laboratory (NINS) are using artificial intelligence to develop a smart system to predict Alzheimer's disease early. According to a report in Journal of Alzheimer's Disease, Professor Pravat Mandal are working to develop a model to map metabolic patterns in different brain regions in healthy and pathological conditions. Alzheimer's is the most common form of dementia, a general term for memory loss and other cognitive abilities serious enough to interfere with daily life. The greatest known risk factor is increasing age, and the majority of people with Alzheimer's are 65 and older. But Alzheimer's is not just a disease of old age.