The number of non-Japanese children at public schools who are lacking in Japanese language skills and who need remedial lessons hit a record 34,335 as of May last year, the latest survey by the education ministry showed Tuesday. The number, up 17.6 percent from the previous biennial survey conducted in 2014, accounted for 42.9 percent of the 80,119 non-Japanese children at public elementary schools, high schools and other public facilities across the country, according to the survey. The Ministry of Education, Culture, Sports, Science and Technology conducted the survey covering about 35,000 public schools. The survey looks at children who cannot hold simple daily conversations in Japanese and/or those who have difficulty learning at school due to poor secondary language skills. "We have taken various measures, such as training teachers and allocating Japanese-language lecturers at schools. But the number of (foreign) children is growing so fast that we have been unable to catch up with it," Yasuhiro Obata, head of at the International Education Division of the ministry, said in a phone interview with The Japan Times.

NEW YORK--Microsoft will be awfully pleased to learn that the burgundy Surface Laptop sitting on a table in my house tickled the fancy of just the type of consumer the company would like to attract: my 13-year old daughter Sydney, a middle-schooler. Indeed, I expect the computer to pose a strong challenge to Google's Chromebook's and Apple's various MacBooks in the classroom, especially if teachers and students embrace the new streamlined version of Windows 10 called Windows 10 S. To be fair, most Apple notebooks use a proprietary adapter as well. You might also consider spend $1,299 for a system with 8GB of RAM and 256GB of storage, double the capacities of the base unit, and the configuration I tested. You can configure even higher priced systems. Surface Laptop ranks among the best looking laptops I've seen and of equal importance is a pleasure to use.

Feature selection is useful on a variety of fronts: it is the best weapon against the Curse of Dimensionality; it can reduce overall training times; and it is a powerful defense against overfitting, increasing model generalizability. After some experiences, using stacked neural nets, parallel neural nets, asymmetric configs, simple neural nets, multiple layers, dropouts, activation functions etc there is one conclusion: There's NOTHING like a good Feature Selection. Accuracy and generalization power can be leveraged by a correct feature selection, based in correlation, skewness, t-test, ANOVA, entropy and information gain. In a time when ample processing power can tempt us to think that feature selection may not be as relevant as it once was, it's important to remember that this only accounts for one of the numerous benefits of informed feature selection -- decreased training times.

In recent years, we have become increasingly good at training deep neural networks to learn a very accurate mapping from inputs to outputs, whether they are images, sentences, label predictions, etc. from large amounts of labeled data. What our models still frightfully lack is the ability to generalize to conditions that are different from the ones encountered during training. Every time you apply your model not to a carefully constructed dataset but to the real world. The real world is messy and contains an infinite number of novel scenarios, many of which your model has not encountered during training and for which it is in turn ill-prepared to make predictions. The ability to transfer knowledge to new conditions is generally known as transfer learning and is what we will discuss in the rest of this post. Over the course of this blog post, I will first contrast transfer learning with machine learning's most pervasive and successful paradigm, supervised learning. I will then outline reasons why transfer learning warrants our attention. Subsequently, I will give a more technical definition and detail different transfer learning scenarios. I will then provide examples of applications of transfer learning before delving into practical methods that can be used to transfer knowledge.

Microsoft Research Asia in collaboration with Chinese Science Academy and Peiching Union University has developed a prototype which translates sign language into spoken language and spoken language into sign language in real-time. This revolutionary technique will enable hearing-impaired individuals to communicate effectively by simply using sign language. Similarly, Microsoft Seeing AI is aimed at helping people who are visually-impaired to understand more about who and what is around them. A research project, Seeing AI, combines image recognition and natural language processing to describe a person's surroundings, read text, answer questions and even identify emotions on people's faces. Seeing AI can be used through smartphone app or smart glass app and can help people to achieve more.

In the paradigm of online learning, a learning algorithm makes a sequence of predictions given the (possibly incomplete) knowledge of the correct answers for the past queries. In contrast to statistical learning, online learning algorithms typically offer distribution-free guarantees. Consequently, online learning algorithms are well suited to dynamic and adversarial environments, where real-time learning from changing data is essential making them ubiquitous in practical applications such as servicing search advertisements.

We present a novel algorithm that synthesizes imperative programs for introductory programming courses. Given a set of input-output examples and a partial program, our algorithm generates a complete program that is consistent with every example. Our key idea is to combine enumerative program synthesis and static analysis, which aggressively prunes out a large search space while guaranteeing to find, if any, a correct solution. We have implemented our algorithm in a tool, called SIMPL, and evaluated it on 30 problems used in introductory programming courses. The results show that SIMPL is able to solve the benchmark problems in 6.6 seconds on average.

Don't know where or how to start learning? But learning more about artificial intelligence, and the myriad overlapping and related fields and application domains does not require a PhD. Getting started can be intimidating, but don't be discouraged; check out this motivating and inspirational post, the author of which went from little understanding of machine learning to actively and effectively utilizing techniques in their job within a year. With more and more institutes of higher learning today making the decision to allow course materials to be openly accessible to non-students via the magic of the web, all of a sudden a pseudo-university course experience can be had by almost anyone, anywhere. Have a look at the following free course materials, all of which are appropriate for an introductory level of AI understanding, some of which also cover niche application concepts and material.

This spring, I taught a class on Machine Learning the Future at Cornell Tech covering a number of advanced topics in machine learning including online learning, joint (structured) prediction, active learning, contextual bandit learning, logarithmic time prediction, and parallel learning. Each of these classes was recorded from the laptop via Zoom and I just uploaded the recordings to Youtube. In some ways, this class is a followup to the large scale learning class I taught with Yann LeCun 4 years ago. The videos for that class were taken down(*) so these lectures both update and replace shared subjects as well as having some new subjects. Much of this material is fairly close to research so to assist other machine learning lecturers around the world in digesting the material, I've made all the source available as well.

Created by a team of Stanford psychologists and AI experts, Woebot uses brief daily chat conversations, mood tracking, curated videos, and word games to help people manage mental health. Scientists who recently looked at text-chat as a supplement to videoconferencing therapy sessions observed that the texting option actually reduced interpersonal anxiety, allowing patients to more fully disclose and discuss issues shrouded in shame, guilt, and embarrassment. Yesterday, Darcy and a team of co-authors at Stanford published a peer-reviewed study in the Journal of Medical Internet Research, Mental Health that randomized 70 college students and asked them to engage with Woebot or a self-help e-book for two weeks. But using those results to claim it can significantly reduce depression may expose Woebot to legal liabilities that bots in supporting roles have managed to avoid.