Microsoft Corp's largest research lab for artificial intelligence and internet of things is scheduled to begin operations in Shanghai on May 15, according to a senior company executive. Known as the Microsoft AI&IoT Insider Lab, the facility is expected to help more than 300 corporate clients turn their prototypes into products every year, said Hsiao-Wuen Hon, vice-president of Microsoft and the managing director of Microsoft Research Asia. Located on the "AIsland", a specialized AI hub in the Zhangjiang Science City in Shanghai's Pudong New Area, the lab is designed to deepen the integration of AI and IoT by providing companies with hardware and software assistance as well as cloud and AI solutions. Hon said Shanghai has been a pioneering force in the country's reform and opening-up and has an advantage in the deployment of AI. "Local authorities have been engaged in the discussion of developing AI since a long time ago and Zhangjiang's AI deployment is highly visionary," he said. The US tech giant announced the establishment of its third such lab in Shanghai in January.

What makes artificial intelligence intelligent? Is it able to learn from errors or recognize, say, the letters of the alphabet in a set of random shapes like a human can? These are some of the questions developers of AI ask. What began as sluggish programs on hulking machines has taken the form of code that anyone in a particular field could test out and manipulate to suit their needs. Jae Ho Sohn, a radiologist at the University of California at San Francisco, is adapting and working with an AI algorithm to analyze thousands of positron emission tomography (PET) scans to search for early signs of Alzheimer's.

Is workplace surveillance about improving productivity or simply a way to control staff and weed out poor performers? Courtney Hagen Ford, 34, left her job working as a bank teller because she found the surveillance she was under was "dehumanising". Her employer logged her keystrokes and used software to monitor how many of the customers she helped went on to take out loans and fee-paying accounts. "The sales pressure was relentless," she recalls. She decided selling fast food would be better, but ironically, left the bank to do a doctorate in surveillance technology.

At an industry conference for video game developers in late March, the thousands of lanyarded attendees could try new games, swap business cards and hear from experts on rendering realistic blood spatter. Or they could talk about unionizing. Hundreds joined a series of standing-room-only roundtables on the topic of organized labor, taking time away from the Game Developers Conference to brainstorm ways to build worker power in an industry that is almost entirely nonunion. Organizers with Game Workers Unite, a group that has sprung up in the last year to push for wall-to-wall unionization in the $43-billion game industry, kicked off each session with an icebreaker: "Damn the man." "Damn the man" for making designers work 100-hour weeks for months on end to deliver a game on time -- a practice known as "crunch" that often comes without overtime or bonus pay.

Recent research on Software-Defined Networking (SDN) strongly promotes the adoption of distributed controller architectures. To achieve high network performance, designing a scheduling function (SF) to properly dispatch requests from each switch to suitable controllers becomes critical. However, existing literature tends to design the SF targeted at specific network settings. In this paper, a reinforcement-learning-based (RL) approach is proposed with the aim to automatically learn a general, effective, and efficient SF. In particular, a new dispatching system is introduced in which the SF is represented as a neural network that determines the priority of each controller. Based on the priorities, a controller is selected using our proposed probability selection scheme to balance the trade-off between exploration and exploitation during learning. In order to train a general SF, we first formulate the scheduling function design problem as an RL problem. Then a new training approach is developed based on a state-of-the-art deep RL algorithm. Our simulation results show that our RL approach can rapidly design (or learn) SFs with optimal performance. Apart from that, the trained SF can generalize well and outperforms commonly used scheduling heuristics under various network settings.

The problem of explaining the behavior of deep neural networks has gained a lot of attention over the last years. While several attribution methods have been proposed, most come without strong theoretical foundations. This raises the question of whether the resulting attributions are reliable. On the other hand, the literature on cooperative game theory suggests Shapley values as a unique way of assigning relevance scores such that certain desirable properties are satisfied. Previous works on attribution methods also showed that explanations based on Shapley values better agree with the human intuition. Unfortunately, the exact evaluation of Shapley values is prohibitively expensive, exponential in the number of input features. In this work, by leveraging recent results on uncertainty propagation, we propose a novel, polynomial-time approximation of Shapley values in deep neural networks. We show that our method produces significantly better approximations of Shapley values than existing state-of-the-art attribution methods.

The Tangent Works team participated in GEFCom 2017 to test its automatic model building strategy for time series known as Tangent Information Modeller (TIM). Model building using TIM combined with historical temperature shuffling resulted in winning the competition. This strategy involved one remaining degree of freedom, a decision on using a trend variable. This paper describes our modelling efforts in the competition, and furthermore outlines a fully automated scenario where the decision on using the trend variable is handled by TIM. The results show that such a setup would also win the competition.

Recently, distant supervision has gained great success on Fine-grained Entity Typing (FET). Despite its efficiency in reducing manual labeling efforts, it also brings the challenge of dealing with false entity type labels, as distant supervision assigns labels in a context agnostic manner. Existing works alleviated this issue with partial-label loss, but usually suffer from confirmation bias, which means the classifier fit a pseudo data distribution given by itself. In this work, we propose to regularize distantly supervised models with Compact Latent Space Clustering (CLSC) to bypass this problem and effectively utilize noisy data yet. Our proposed method first dynamically constructs a similarity graph of different entity mentions; infer the labels of noisy instances via label propagation. Based on the inferred labels, mention embeddings are updated accordingly to encourage entity mentions with close semantics to form a compact cluster in the embedding space,thus leading to better classification performance. Extensive experiments on standard benchmarks show that our CLSC model consistently outperforms state-of-the-art distantly supervised entity typing systems by a significant margin.

An increasing amount of civil engineering applications are utilising data acquired from infrastructure instrumented with sensing devices. This data has an important role in monitoring the response of these structures to excitation, and evaluating structural health. In this paper we seek to monitor pedestrian-events (such as a person walking) on a footbridge using strain and acceleration data. The rate of this data acquisition and the number of sensing devices make the storage and analysis of this data a computational challenge. We introduce a streaming method to compress the sensor data, whilst preserving key patterns and features (unique to different sensor types) corresponding to pedestrian-events. Numerical demonstrations of the methodology on data obtained from strain sensors and accelerometers on the pedestrian footbridge are provided to show the trade-off between compression and accuracy during and in-between periods of pedestrian-events.

In this paper, we consider advancing web-scale knowledge extraction and alignment by integrating OpenIE extractions in the form of (subject, predicate, object) triples with Knowledge Bases (KB). Traditional techniques from universal schema and from schema mapping fall in two extremes: either they perform instance-level inference relying on embedding for (subject, object) pairs, thus cannot handle pairs absent in any existing triples; or they perform predicate-level mapping and completely ignore background evidence from individual entities, thus cannot achieve satisfying quality. We propose OpenKI to handle sparsity of OpenIE extractions by performing instance-level inference: for each entity, we encode the rich information in its neighborhood in both KB and OpenIE extractions, and leverage this information in relation inference by exploring different methods of aggregation and attention. In order to handle unseen entities, our model is designed without creating entity-specific parameters. Extensive experiments show that this method not only significantly improves state-of-the-art for conventional OpenIE extractions like ReVerb, but also boosts the performance on OpenIE from semi-structured data, where new entity pairs are abundant and data are fairly sparse.