I will also discuss the common technical challenges of executing A/B tests on ML algorithms, such as infrastructure requirements, connecting online and offline metrics, and handling ramp up periods for online learning algorithms. Overall, the goal of this talk will be to motivate ML practitioners to use A/B testing when evaluating their algorithms and provide them with high-level guidelines on how to do it. Profile Pavel Dmitriev is a Vice President of Data Science at Outreach, where he works on enabling data driven decision making in sales through experimentation and machine learning. He was previously a Principal Data Scientist with Microsoft's Analysis and Experimentation team, where he worked on scaling experimentation in Bing, Skype, and Windows OS. Pavel co-authored numerous papers at top-tier data mining and machine learning conferences, such as WWW, ICSE, KDD, has given keynotes and tutorials at WWW, SIGIR, SEAA, and KDD.

SPRINGFIELD, MASSACHUSETTS – Police departments around the U.S. are asking citizens to trust them to use facial recognition software as another handy tool in their crime-fighting toolbox. But some lawmakers -- and even some technology giants -- are hitting the brakes. Are fears of an all-seeing, artificially intelligent security apparatus overblown? Not if you look at China, where advancements in computer vision applied to vast networks of street cameras have enabled authorities to track members of ethnic minority groups for signs of subversive behavior. American police officials and their video surveillance industry partners contend that won't happen here.

Toyota Motor Corp. plans to first deploy advanced self-driving features in commercial vehicles before adding them to cars meant for personal use, a senior official at the Japanese auto major said on Tuesday. It will be easier to apply self-driving technology that does not require constant and direct human-monitoring to taxis and vehicles Toyota is developing, including on-demand ride services, mobile shops and ambulatory hospitals, said James Kuffner, chief of Toyota Research Institute-Advanced Development (TRI-AD). The operators of these vehicles could control when and where they are deployed and oversee their maintenance, he told reporters at the opening of its new offices in Tokyo. "It will take more time to achieve'Level 4' for a personally-owned vehicle," Kuffner said, referring to the automation level at which vehicles can drive themselves under limited conditions. "Level 4 is really what we're striving for to first appear in mobility as a service," he added.

The simultaneous control of multiple coordinated robotic agents represents an elaborate problem. If solved, however, the interaction between the agents can lead to solutions to sophisticated problems. The concept of swarming, inspired by nature, can be described as the emergence of complex system-level behaviors from the interactions of relatively elementary agents. Due to the effectiveness of solutions found in nature, bio-inspired swarming-based control techniques are receiving a lot of attention in robotics. One method, known as swarm shepherding, is founded on the sheep herding behavior exhibited by sheepdogs, where a swarm of relatively simple agents are governed by a shepherd (or shepherds) which is responsible for high-level guidance and planning. Many studies have been conducted on shepherding as a control technique, ranging from the replication of sheep herding via simulation, to the control of uninhabited vehicles and robots for a variety of applications. We present a comprehensive review of the literature on swarm shepherding to reveal the advantages and potential of the approach to be applied to a plethora of robotic systems in the future.

When and why can a neural network be successfully trained? This article provides an overview of optimization algorithms and theory for training neural networks. First, we discuss the issue of gradient explosion/vanishing and the more general issue of undesirable spectrum, and then discuss practical solutions including careful initialization and normalization methods. Second, we review generic optimization methods used in training neural networks, such as SGD, adaptive gradient methods and distributed methods, and theoretical results for these algorithms. Third, we review existing research on the global issues of neural network training, including results on bad local minima, mode connectivity, lottery ticket hypothesis and infinite-width analysis.

Neural network compression methods have enabled deploying large models on emerging edge devices with little cost, by adapting already-trained models to the constraints of these devices. The rapid development of AI-capable edge devices with limited computation and storage requires streamlined methodologies that can efficiently satisfy the constraints of different devices. In contrast, existing methods often rely on heuristic and manual adjustments to maintain accuracy, support only coarse compression policies, or target specific device constraints that limit their applicability. We address these limitations by proposing the TOlerance-based COmpression (TOCO) framework. TOCO uses an in-depth analysis of the model, to maintain the accuracy, in an active learning system. The results of the analysis are tolerances that can be used to perform compression in a fine-grained manner. Finally, by decoupling compression from the tolerance analysis, TOCO allows flexibility to changes in the hardware.

Fingerprinting-based positioning, one of the promising indoor positioning solutions, has been broadly explored owing to the pervasiveness of sensor-rich mobile devices, the prosperity of opportunistically measurable location-relevant signals and the progress of data-driven algorithms. One critical challenge is to controland improve the quality of the reference fingerprint map (RFM), which is built at the offline stage and applied for online positioning. The key concept concerningthe quality control of the RFM is updating the RFM according to the newly measured data. Though varies methods have been proposed for adapting the RFM, they approach the problem by introducing extra-positioning schemes (e.g. PDR orUGV) and directly adjust the RFM without distinguishing whether critical changes have occurred. This paper aims at proposing an extra-positioning-free solution by making full use of the redundancy of measurable features. Loosely inspired by random sampling consensus (RANSAC), arbitrarily sampled subset of features from the online measurement are used for generating multi-resamples, which areused for estimating the intermediate locations. In the way of resampling, it can mitigate the impact of the changed features on positioning and enables to retrieve accurate location estimation. The users location is robustly computed by identifying the candidate locations from these intermediate ones using modified Jaccardindex (MJI) and the feature-wise change belief is calculated according to the world model of the RFM and the estimated variability of features. In order to validate our proposed approach, two levels of experimental analysis have been carried out. On the simulated dataset, the average change detection accuracy is about 90%. Meanwhile, the improvement of positioning accuracy within 2 m is about 20% by dropping out the features that are detected as changed when performing positioning comparing to that of using all measured features for location estimation. On the long-term collected dataset, the average change detection accuracy is about 85%.

Taking an answer and its context as input, sequence-to- sequence models have made considerable progress on question generation. However, we observe that these approaches often generate wrong question words or keywords and copy answer-irrelevant words from the input. We believe that lacking global question semantics and exploiting answer position-awareness not well are the key root causes. In this paper, we propose a neural question generation model with two concrete modules: sentence-level semantic matching and answer position inferring. Further, we enhance the initial state of the decoder by leveraging the answer-aware gated fusion mechanism. Experimental results demonstrate that our model outperforms the state-of-the-art (SOT A) models on SQuAD and MARCO datasets. Owing to its generality, our work also improves the existing models significantly.

Graph clustering groups entities -- the vertices of a graph -- based on their similarity, typically using a complex distance function over a large number of features. Successful integration of clustering approaches in automated decision-support systems hinges on the interpretability of the resulting clusters. This paper addresses the problem of generating interpretable clusters, given features of interest that signify interpretability to an end-user, by optimizing interpretability in addition to common clustering objectives. We propose a $\beta$-interpretable clustering algorithm that ensures that at least $\beta$ fraction of nodes in each cluster share the same feature value. The tunable parameter $\beta$ is user-specified. We also present a more efficient algorithm for scenarios with $\beta\!=\!1$ and analyze the theoretical guarantees of the two algorithms. Finally, we empirically demonstrate the benefits of our approaches in generating interpretable clusters using four real-world datasets. The interpretability of the clusters is complemented by generating simple explanations denoting the feature values of the nodes in the clusters, using frequent pattern mining.

We propose an explainable reinforcement learning (XRL) framework that analyzes an agent's history of interaction with the environment to extract interestingness elements that help explain its behavior. The framework relies on data readily available from standard RL algorithms, augmented with data that can easily be collected by the agent while learning. We describe how to create visual explanations of an agent's behavior in the form of short video-clips highlighting key interaction moments, based on the proposed elements. We also report on a user study where we evaluated the ability of humans in correctly perceiving the aptitude of agents with different characteristics, including their capabilities and limitations, given explanations automatically generated by our framework. The results show that the diversity of aspects captured by the different interestingness elements is crucial to help humans correctly identify the agents' aptitude in the task, and determine when they might need adjustments to improve their performance.