Learning representation has been proven to be helpful in numerous machine learning tasks. The success of the majority of existing representation learning approaches often requires a large amount of consistent and noise-free labels. However, labels are not accessible in many real-world scenarios and they are usually annotated by the crowds. In practice, the crowdsourced labels are usually inconsistent among crowd workers given their diverse expertise and the number of crowdsourced labels is very limited. Thus, directly adopting crowdsourced labels for existing representation learning algorithms is inappropriate and suboptimal. In this paper, we investigate the above problem and propose a novel framework of \textbf{R}epresentation \textbf{L}earning with crowdsourced \textbf{L}abels, i.e., "RLL", which learns representation of data with crowdsourced labels by jointly and coherently solving the challenges introduced by limited and inconsistent labels. The proposed representation learning framework is evaluated in two real-world education applications. The experimental results demonstrate the benefits of our approach on learning representation from limited labeled data from the crowds, and show RLL is able to outperform state-of-the-art baselines. Moreover, detailed experiments are conducted on RLL to fully understand its key components and the corresponding performance.

This paper investigates different vector step-size adaptation approaches for non-stationary online, continual prediction problems. Vanilla stochastic gradient descent can be considerably improved by scaling the update with a vector of appropriately chosen step-sizes. Many methods, including AdaGrad, RMSProp, and AMSGrad, keep statistics about the learning process to approximate a second order update---a vector approximation of the inverse Hessian. Another family of approaches use meta-gradient descent to adapt the step-size parameters to minimize prediction error. These meta-descent strategies are promising for non-stationary problems, but have not been as extensively explored as quasi-second order methods. We first derive a general, incremental meta-descent algorithm, called AdaGain, designed to be applicable to a much broader range of algorithms, including those with semi-gradient updates or even those with accelerations, such as RMSProp. We provide an empirical comparison of methods from both families. We conclude that methods from both families can perform well, but in non-stationary prediction problems the meta-descent methods exhibit advantages. Our method is particularly robust across several prediction problems, and is competitive with the state-of-the-art method on a large-scale, time-series prediction problem on real data from a mobile robot.

By now, most people have interacted, often unknowingly, with artificial intelligence (AI) through increasingly ubiquitous chatbots or smart products and devices. Across industries, there is a host of far more intriguing applications of AI emerging in fields such as healthcare, manufacturing, insurance, and professional services. These use cases demonstrate that, far from replacing human intelligence, AI – when employed responsibly – is unleashing human expertise and creativity in ways that deliver tremendous value to the individual, the enterprise and even the community. Gartner projects the global business value derived from AI will reach $3.9tn by 2022, through improved customer experience, new revenue and cost reduction. Gartner predicts that decision automation--harnessing unstructured data to make sense of ambiguity--will be a key driver of this trend, growing from 2% of AI-derived value in 2018 to 16% by 2022.

University of California, Irvine AI/Machine Learning Part-Time Instructor Recruitment Period Open date: February 22nd, 2019 Last review date: Friday, Mar 1, 2019 at 11:59pm (Pacific Time) Applications received after this date will be reviewed by the search committee if the position has not yet been filled. Final date: Saturday, Feb 22, 2020 at 11:59pm (Pacific Time) Applications will continue to be accepted until this date, but those received after the review date will only be considered if the position has not yet been filled. Description At the University of California Irvine's Department of Continuing Education - Technology Programs, our mission is to provide the best technical professional development courses online. We are laser focused on inspiring our students to learn new technical coding skills and shaping the future for their success. We are passionate about our education programs that support our students to fulfil their career goals and we are empowered to help thousands of people learn online every day.

The "little black dress" has been considered a staple in women's fashion since the designer Coco Chanel popularized it in the 1920s. Since then, it's seen many iterations, most recently, by machine-learning software developed by two recent MIT graduates, called Glitch. Pinar Yanardag and Emily Salvador met at MIT while taking a course called "How to Generate (Almost) Anything," which encouraged students to use deep learning software for creative projects. In that course, they dabbled with creating AI-generated art, perfume and jewelry, and were inspired to start Glitch, a new clothing company that sells pieces designed by AI. "The'little black dress' is considered an essential item that should be in any woman's wardrobe," said Yanardag. "Sooner or later, AI is going to be an essential tool for any person in computing, so we thought the'little black dress' was a good place to start."

Bankers are rushing to take Oxford University's courses on fintech, blockchain strategy, algorithmic trading, and artificial intelligence before robots take their jobs. More than 9,000 people from upwards of 135 countries have taken the online open courses, which focus on digital transformation in business, at the university's Saïd Business School, a spokesperson told Markets Insider. The fintech course, the first of five to be launched, has run 12 times and attracted nearly 4,300 students in less than two years. The average age of participants across the courses is 39, and two-thirds of them came from the financial services sector, suggesting experienced professionals are returning to school to understand how their industry is being disrupted and learn the skills needed to weather the changes. Bankers' fears of being replaced by robots are well founded.

In recent years, the use of data-driven modelling and integration of behavioural and psychological factors in discrete choice and travel behaviour analysis have become active areas of research [2, 3, 4]. In the context of data-driven models, behavioural variations describe the correlation between observed choice attributes and unobserved socioeconomic factors using a flexible and tractable model specification. These variations include: decision-protocols, choice sets, unobserved taste variations and unobserved attributes [5]. Under these considerations, recent studies on travel behaviour analysis have so far primarily focused on representing heterogeneity in the error correction function and incorporating it into utility based multinomial logit (MNL) models [3]. Models such as mixed multinomial logit (MMNL) or latent class (LC) model offers flexibility in representing heterogeneity and substitution patterns. In addition, recent conceptual frameworks such as the integrated choice and latent variable (ICLV) use individuals' psychometric indicators to represent unobserved behavioural and perception heterogeneity [6]. It is also possible to apply a generative machine learning to identify informative latent constructs in travel decision making without subjective behaviour indicators [7, 8]. However, the true underlying behavioural patterns are often unknown and usually approximated by some predetermined exogenous indicator variables that would often lead to model misspecification due to lack of complete information, or error in data collection [9]. Furthermore, accurate specification of the underlying distribution assumes individuals have access to all available information regarding the travel activity (e.g.

Among the data-efficient approaches for online adaptation in robotics (meta-learning, model-based reinforcement learning, etc.), repertoire-based learning (1) generates a large and diverse set policies in simulation that acts as a "reservoir" for future adaptations and (2) learns to pick online the best working policies according to the current situation (e.g., a damaged robot, a new object, etc.). Each of these policies performs a different task, for instance, walking in different directions; these policies are then sequenced with a planning algorithm to achieve the given task. In this paper, we relax the assumption of previous works that a single repertoire is enough for adaptation. Instead, we generate repertoires for many different situations (e.g., with a missing leg, on different floors, etc.) in simulation that act as priors for adaptation. Our main contribution is an algorithm, APROL (Adaptive Prior selection for Repertoire-based Online Learning) to plan the next action by incorporating these priors when the robot has no information about the current situation. We evaluate APROL on two simulated tasks: (1) pushing unknown objects of various shapes and sizes with a kuka arm and (2) a goal reaching task with a damaged hexapod robot. We compare with "Reset-free Trial and Error" (RTE) and various single repertoire-based baselines. The results show that APROL solves both tasks in less interaction time than the baselines. Additionally, we demonstrate APROL on a real, damaged hexapod that quickly learns compensatory policies to reach a goal by avoiding obstacle in the path.

Predicting firm's failure is one of the most interesting subjects for investors and decision makers. In this paper, a bankruptcy prediction model is proposed based on Artificial Neural networks (ANN). Taking into consideration that the choice of v ariables to discriminate between bankrupt and non - bankrupt firms influences significantly the model's accuracy and considering the problem of local minima, we propose a hybrid ANN based on variables selection techniques. Moreover, we evolve the convergence of Particle Swarm Optimization (PSO) by proposing a training algorithm based on an improved PSO and Simulated Annealing. A comparative performance study is reported, and the proposed hybrid model shows a high performance and convergence in the context of missing data.

Pedestrian dynamics is an interdisciplinary field of research. Psychologists, sociologists, traffic engineers, physicists, mathematicians and computer scientists all strive to understand the dynamics of a moving crowd. In principle, computer simulations offer means to further this understanding. Yet, unlike for many classic dynamical systems in physics, there is no universally accepted locomotion model for crowd dynamics. On the contrary, a multitude of approaches, with very different characteristics, compete. Often only the experts in one special model type are able to assess the consequences these characteristics have on a simulation study. Therefore, scientists from all disciplines who wish to use simulations to analyze pedestrian dynamics need a tool to compare competing approaches. Developers, too, would profit from an easy way to get insight into an alternative modeling ansatz. Vadere meets this interdisciplinary demand by offering an open-source simulation framework that is lightweight in its approach and in its user interface while offering pre-implemented versions of the most widely spread models.