User intended actions are widely seen in many areas. Forecasting these actions and taking proactive measures to optimize business outcome is a crucial step towards sustaining the steady business growth. In this work, we focus on pre- dicting attrition, which is one of typical user intended actions. Conventional attrition predictive modeling strategies suffer a few inherent drawbacks. To overcome these limitations, we propose a novel end-to-end learning scheme to keep track of the evolution of attrition patterns for the predictive modeling. It integrates user activity logs, dynamic and static user profiles based on multi-path learning. It exploits historical user records by establishing a decaying multi-snapshot technique. And finally it employs the precedent user intentions via guiding them to the subsequent learning procedure. As a result, it addresses all disadvantages of conventional methods. We evaluate our methodology on two public data repositories and one private user usage dataset provided by Adobe Creative Cloud. The extensive experiments demonstrate that it can offer the appealing performance in comparison with several existing approaches as rated by different popular metrics. Furthermore, we introduce an advanced interpretation and visualization strategy to effectively characterize the periodicity of user activity logs. It can help to pinpoint important factors that are critical to user attrition and retention and thus suggests actionable improvement targets for business practice. Our work will provide useful insights into the prediction and elucidation of other user intended actions as well.

In many settings, a decision-maker wishes to learn a rule, or policy, that maps from observable characteristics of an individual to an action. Examples include selecting offers, prices, advertisements, or emails to send to consumers, as well as the problem of determining which medication to prescribe to a patient. While there is a growing body of literature devoted to this problem, most existing results are focused on the case where data comes from a randomized experiment, and further, there are only two possible actions, such as giving a drug to a patient or not. In this paper, we study the offline multi-action policy learning problem with observational data and where the policy may need to respect budget constraints or belong to a restricted policy class such as decision trees. We build on the theory of efficient semi-parametric inference in order to propose and implement a policy learning algorithm that achieves asymptotically minimax-optimal regret. To the best of our knowledge, this is the first result of this type in the multi-action setup, and it provides a substantial performance improvement over the existing learning algorithms. We then consider additional computational challenges that arise in implementing our method for the case where the policy is restricted to take the form of a decision tree. We propose two different approaches, one using a mixed integer program formulation and the other using a tree-search based algorithm.

In multi-task learning, multiple tasks are solved jointly, sharing inductive bias between them. Multi-task learning is inherently a multi-objective problem because different tasks may conflict, necessitating a trade-off. A common compromise is to optimize a proxy objective that minimizes a weighted linear combination of per-task losses. However, this workaround is only valid when the tasks do not compete, which is rarely the case. In this paper, we explicitly cast multi-task learning as multi-objective optimization, with the overall objective of finding a Pareto optimal solution. To this end, we use algorithms developed in the gradient-based multi-objective optimization literature. These algorithms are not directly applicable to large-scale learning problems since they scale poorly with the dimensionality of the gradients and the number of tasks. We therefore propose an upper bound for the multi-objective loss and show that it can be optimized efficiently. We further prove that optimizing this upper bound yields a Pareto optimal solution under realistic assumptions. We apply our method to a variety of multi-task deep learning problems including digit classification, scene understanding (joint semantic segmentation, instance segmentation, and depth estimation), and multi-label classification. Our method produces higher-performing models than recent multi-task learning formulations or per-task training.

Build accurate DNN models requires training on large labeled, context specific datasets, especially those matching the target scenario. We believe advances in wireless localization, working in unison with cameras, can produce automated annotation of targets on images and videos captured in the wild. Using pedestrian and vehicle detection as examples, we demonstrate the feasibility, benefits, and challenges of an automatic image annotation system. Our work calls for new technical development on passive localization, mobile data analytics, and error-resilient ML models, as well as design issues in user privacy policies.

Over the past decades, deep learning (DL) systems have achieved tremendous success and gained great popularity in various applications, such as intelligent machines, image processing, speech processing, and medical diagnostics. Deep neural networks are the key driving force behind its recent success, but still seem to be a magic black box lacking interpretability and understanding. This brings up many open safety and security issues with enormous and urgent demands on rigorous methodologies and engineering practice for quality enhancement. A plethora of studies have shown that the state-of-the-art DL systems suffer from defects and vulnerabilities that can lead to severe loss and tragedies, especially when applied to real-world safety-critical applications. In this paper, we perform a large-scale study and construct a paper repository of 223 relevant works to the quality assurance, security, and interpretation of deep learning. We, from a software quality assurance perspective, pinpoint challenges and future opportunities towards universal secure deep learning engineering. We hope this work and the accompanied paper repository can pave the path for the software engineering community towards addressing the pressing industrial demand of secure intelligent applications.

AI can significantly enhance the learning experience thanks to learning-specific algorithms, compared to those that we're already aware of, particularly those that power AI-enabled consumer products, such as smart home assistants (Google Home, Amazon Alexa) or social media platforms that use AI to turn text into emojis on your smartphone. In the context of learning, deploying AI requires algorithms powered by a fine-tuned combination of machine learning, deep learning and natural language processing. The benefits of AI will be felt in any number of ways in enterprise learning, but we've identified five that you should start to understand as soon as you can. Additionally, AI would help learners uncover resources by suggesting various learning assets, eliminating the time and effort it would take to do this task manually. AI-enabled systems "hear" and understand language as complete sentences and their connotations while a learner talks to the learning platform.

The Information Sciences Institute (ISI) is a unit of the University of Southern California's highly ranked Viterbi School of Engineering. ISI is one of the nation's largest, most successful university-affiliated computer research institutes. The Video, Image, Speech and Text Analytics (VISTA) group at ISI has spent the past three years advancing the state of research for facial recognition, a technology with significant implications for security and commerce. In order to conduct this research, "We needed a reliable, powerful workload management platform that would enhance performance and have the ability to run complex, diverse workloads across multiple users within the entire ISI organization," said Stephen Rawls, programmer and research analyst. VISTA selected Univa Grid Engine and cites key contributing factors over other vendors: built-in advanced GPU support, detailed documentation, ongoing product upgrades and customer support.

Abstract: Engineers, as implementers of technology, are highly complementary to the intangible knowledge assets that firms accumulate. This paper seeks to address whether technical talent is a source of rents for corporate employers, both in general and in the specific case of the surprising open-source launch of TensorFlow, a deep learning software package, by Google. Using over 180 million position records and over 52 million skill records from LinkedIn, I build a panel of firm-level investment in technological human capital (information technology, research, and engineering talent quantities). I find that on average, an additional engineer at a firm is correlated with approximately $854,000 more market value. The second part of the talk covers the launch of TensorFlow, an open-source machine learning package created by Google, and its effect on the market value of firms with AI Talent.

A robot is set to become the first non-human to appear as a witness before the UK Parliament. The Commons Education Select Committee invited Pepper the robot from Middlesex University to give evidence at a hearing taking place next week about artificial intelligence, robotics and the fourth industrial revolution. "If we've got the march of the robots, we perhaps need the march of the robots to our select committee to give evidence," Committee chair Robert Halfon told Tes. "The fourth industrial revolution is possibly the most important challenge facing our nation over the next 10, 20 to 30 years." The Independent has reached out for more details about the appearance. Despite dystopian predictions and dire warnings of robots and AI taking over people's jobs, the government has previously expressed interest in the potential of robotic technology.

"Data science" is hot right now. The number of undergraduate degrees in statistics has tripled in the past decade, and as a statistics professor, I can tell you that it isn't because freshmen love statistics. Way back in 2009, economist Hal Varian of Google dubbed statistician the "next sexy job." Since then, statistician, data scientist and actuary have topped various "best jobs" lists. Not to mention the enthusiastic press coverage of industry applications: Machine learning! But is it good advice?