This paper considers the problem of recognizing eating gestures by tracking wrist motion. Eating gestures can have large variability in motion depending on the subject, utensil, and type of food or beverage being consumed. Previous works have shown viable proofs-of-concept of recognizing eating gestures in laboratory settings with small numbers of subjects and food types, but it is unclear how well these methods would work if tested on a larger population in natural settings. As more subjects, locations and foods are tested, a larger amount of motion variability could cause a decrease in recognition accuracy. To explore this issue, this paper describes the collection and annotation of 51,614 eating gestures taken by 269 subjects eating a meal in a cafeteria. Experiments are described that explore the complexity of hidden Markov models (HMMs) and the amount of training data needed to adequately capture the motion variability across this large data set. Results found that HMMs needed a complexity of 13 states and 5 Gaussians to reach a plateau in accuracy, signifying that a minimum of 65 samples per gesture type are needed. Results also found that 500 training samples per gesture type were needed to identify the point of diminishing returns in recognition accuracy. Overall, the findings provide evidence that the size a data set typically used to demonstrate a laboratory proofs-of-concept may not be sufficiently large enough to capture all the motion variability that could be expected in transitioning to deployment with a larger population. Our data set, which is 1-2 orders of magnitude larger than all data sets tested in previous works, is being made publicly available.

In 2016, the majority of full-time employed women in the U.S. earned significantly less than comparable men. The extent to which women were affected by gender inequality in earnings, however, depended greatly on socio-economic characteristics, such as marital status or educational attainment. In this paper, we analyzed data from the 2016 American Community Survey using a high-dimensional wage regression and applying double lasso to quantify heterogeneity in the gender wage gap. We found that the gap varied substantially across women and was driven primarily by marital status, having children at home, race, occupation, industry, and educational attainment. We recommend that policy makers use these insights to design policies that will reduce discrimination and unequal pay more effectively.

Current generation of memory-augmented neural networks has limited scalability as they cannot efficiently process data that are too large to fit in the external memory storage. One example of this is lifelong learning scenario where the model receives unlimited length of data stream as an input which contains vast majority of uninformative entries. We tackle this problem by proposing a memory network fit for long-term lifelong learning scenario, which we refer to as Long-term Episodic Memory Networks (LEMN), that features a RNN-based retention agent that learns to replace less important memory entries based on the retention probability generated on each entry that is learned to identify data instances of generic importance relative to other memory entries, as well as its historical importance. Such learning of retention agent allows our long-term episodic memory network to retain memory entries of generic importance for a given task. We validate our model on a path-finding task as well as synthetic and real question answering tasks, on which our model achieves significant improvements over the memory augmented networks with rule-based memory scheduling as well as an RL-based baseline that does not consider relative or historical importance of the memory.

The question addressed in this paper is: If we present to a user an AI system that explains how it works, how do we know whether the explanation works and the user has achieved a pragmatic understanding of the AI? In other words, how do we know that an explanainable AI system (XAI) is any good? Our focus is on the key concepts of measurement. We discuss specific methods for evaluating: (1) the goodness of explanations, (2) whether users are satisfied by explanations, (3) how well users understand the AI systems, (4) how curiosity motivates the search for explanations, (5) whether the user's trust and reliance on the AI are appropriate, and finally, (6) how the human-XAI work system performs. The recommendations we present derive from our integration of extensive research literatures and our own psychometric evaluations.

YANGON – Myanmar's first-ever training course for Japanese-language teachers is opening as part of Prime Minister Shinzo Abe's plan to invite more Asian youths to work in Japan. The initial phase of the training program starts this month at the Yangon University of Foreign Languages for students majoring in Japanese and for teachers from private Japanese-language schools, the Japan Foundation said. The foundation, a government-backed institution that carries out international cultural exchange programs, picked Myanmar as the third country in which to offer such training courses, after India and Vietnam, following Abe's speech at an international conference in Tokyo in 2017 where he said Japan would choose three locations in Asia to nurture Japanese-language teachers. Noriyuki Matsukawa, executive director of the Japan Foundation Center for Japanese Language Testing, said the yearlong program aims to support Myanmar's human resources through Japanese-language learning, recruit a new kind of teacher and improve current teachers' skills. "Myanmar has high demand for Japanese-language proficiency," he said, adding that the number of people in Myanmar taking the Japanese-Language Proficiency Test nearly tripled from 13,099 in 2016 to 37,786 in 2018.

Perhaps he won the presidency thanks to his specialized knowledge of voting behavior and public opinion, or maybe it was his casual tweets in conversations with students, his use of mocking buzzwords or his adoption of slang used by his pupils. Whatever the case, 67-year-old Aiji Tanaka assumed the presidency of Tokyo's Waseda University last month, becoming the institution's first leader selected from the political science and economics department over the past 50 years. Tanaka envisions raising Waseda into the ranks of the world's top schools, with clear measures he says must be "effective first, and then efficient." Tanaka said he intends to boost the university into the top 30 to 40 institutions worldwide. "To be a top university in the world, serious determination and commitment are necessary. That was the first thing I thought of when becoming president," said Tanaka.

There are no hard and fast rules for learning such a complex topic. The beauty of online learning is that you get to choose what you lack and what excite you. For this part 1 of the series, I will review the maths and python fundamental courses that I had taken. Please note that these are my personal opinion which might or might not resonate with you. I like to give special mention to Data Science A-Z by Kirill Eremenko and the SuperDataScience Team.

At Amazon Web Services (AWS), we are continually innovating with new services and solutions. That's why we're excited to announce several new offerings from AWS Training and Certification to help AWS Partner Network (APN) Partners build new cloud skills and learn about the latest AWS services. Dive deep into the same ML curriculum we use to train Amazon's developers and data scientists. Choose from four role-based learning paths, with more than 30 digital ML courses and hands-on labs totaling 45 hours of training. Take our new AWS Certified Machine Learning – Specialty beta exam.

According to surveys, 75% of teachers in USA believe printed books will entirely be replaced by digital learning tools. Is the Internet and technology really a game changer within the education sector? Over the past few decades, new technologies have truly transformed every aspect of our world, from scientific and industrial development to day-to-day activities in our personal space. And, whenever a new technology is introduced to the masses, the way people interact with each other and envision their lives has shifted drastically. The truth is, we only realize the redundancies of our current practices after we are introduced to a new technology that makes our daily activities efficient.

Me: "Alexa, tell me what will happen in 2019." Amazon AI: "Do you want to open'this day in history'?" Me: "Alexa, give me a prediction for 2019." Amazon AI: "The crystal ball is clouded, I can't tell." My conversation with Amazon's "smart speaker" or "intelligent voice assistant" just about sums up the present state of "artificial intelligence" (AI) at home, the office, and the factory: Try a few times and sooner or later you will probably get the correct action the human intelligence behind it programmed it to perform. What will be the state of AI in 2019? The following list features 120 senior executives involved with AI, all peering into their not-so-clouded crystal ball, and promising less hype and more practical, precise, and narrow AI. "Self-Driving Finance is a practical implementation of AI that is already used in one form or another by millions of bank customers around the globe and will only get better in the coming years. Based on projects that are currently underway with ...