The use of facial recognition software is growing in China--s universities, ostensibly to improve security, but concerns are growing that it is used for monitoring students -- including foreing students -- and teachers, creating massive data bases on student attendance and movements around campus. Peking University in Beijing now screens students entering the university--s south-western gate by using a camera to scan their faces in a trial that began at the end of June to see if the technology can replace the use of university identity cards. The system scans through a database of thousands of photographs taken for student and staff identity cards, using a powerful system to match the photograph against a database of thousands of others. Facial recognition devices have already been installed outside the university--s libraries, classrooms, student accommodation, sports facilities and computer centres, but these match a face to an existing photograph of that person on the database rather than sifting through the entire database. Photographs can be retaken in the guard room at the gates if the photos do not quite match, according to the university--s social media account on Sina Weibo, though it does not say what the failure rate is -- in particular for foreign students.

As STEM (science, technology, engineering, and mathematics) education becomes more centered on active learning practices, what happens to students' anxiety levels? Specifically, what aspects of evaluative active learning practices cause student anxiety to increase or decrease? After measuring students' baseline anxiety levels, Cooper et al. conducted semi-structured interviews to explore how students' anxiety levels were altered in an active learning classroom. Results show that the way that the active learning activity is implemented and the extent to which students perceive the activity to be beneficial influence its effect on their anxiety. The authors encourage instructors to consider student anxiety when implementing active learning.

An entrepreneur who follows his father into an established industry is likely to enjoy greater success than peers whose parents didn't work in that field, recent research suggests. At the same time, innovative, high-IQ entrepreneurs are more likely to strike out on their own in search of greater rewards, researchers found after analyzing statistics on young and middle-aged Norwegian men and businesses started in Norway from 1999 to 2007. Their findings indicate that different advantages – inherited industry knowledge for some, great intellectual talent for others – take entrepreneurs on different paths to different kinds of success. "A majority of male entrepreneurs start a firm in the same or a closely related industry as their fathers' industry of employment," the researchers wrote in a National Bureau of Economic Research working paper issued early this year. "This tendency is correlated with intelligence: higher-IQ entrepreneurs are less likely to follow their fathers," they said. In fact, the authors found that entrepreneurs with higher cognitive test scores are far more likely to go into the tech industry.

Our children's education is vital. And we are on the cusp of a pedagogical revolution, an upending of traditional instruction. We must invest now to keep education lock-step with technological progress. Automation, machine learning, and artificial intelligence may be serving up the greatest challenge we have ever faced when it comes to education. As these technologies displace jobs at faster and faster rates, we'll increasingly need a workforce that's adaptable.

Imagine you are a parent whose child is applying to get into school. You'd want your child to have the best possible chance of being accepted at the school of your choice, right? Now, what if you knew that the decision of where to place your child was being made by artificial intelligence (AI). Would you trust an algorithm to have your child's best interests at heart? That's exactly the scenario parents in one of the major Dutch cities have encountered ever since the school system embraced AI to create a more equitable and evenly distributed student allocation system.

Airplanes fly over Xiamen City, southeast China's Fujian Province, July 18, 2018. After a short holiday, we have a lot to catch up on. AI made huge leaps and has made insurance claims 176,000 times more efficient than humans, China has opened their low-altitude airspace for the booming drone industry, and classrooms are getting quantified using AI and brain research. Let's get you the news. Yes, you read that correctly.

Cuban was in conversation with Charlie Kirk, the 24-year-old founder of Turning Point USA, a right-wing non-profit organization aimed at promoting conservative political ideas among high school students. Cuban does not identify as Republican or Democrat: "I don't belong to any political party and I never will," Cuban told Kirk. Amid a wide-ranging debate about what the scope of government should be, Cuban argued that the government should be involved in funding artificial intelligence research. In November, the billionaire warned that the United States should not allow countries like China and Russia to pull ahead in terms of developing artificial intelligence. China's government has said publicly it plans to be the global leader in artificial intelligence by 2030 and Russian President Vladimir Putin has said, "the one who becomes the leader in this sphere will be the ruler of the world."

We explore methods for option discovery based on variational inference and make two algorithmic contributions. First: we highlight a tight connection between variational option discovery methods and variational autoencoders, and introduce Variational Autoencoding Learning of Options by Reinforcement (VALOR), a new method derived from the connection. In VALOR, the policy encodes contexts from a noise distribution into trajectories, and the decoder recovers the contexts from the complete trajectories. Second: we propose a curriculum learning approach where the number of contexts seen by the agent increases whenever the agent's performance is strong enough (as measured by the decoder) on the current set of contexts. We show that this simple trick stabilizes training for VALOR and prior variational option discovery methods, allowing a single agent to learn many more modes of behavior than it could with a fixed context distribution. Finally, we investigate other topics related to variational option discovery, including fundamental limitations of the general approach and the applicability of learned options to downstream tasks.

Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to leverage useful information contained in multiple related tasks to help improve the generalization performance of all the tasks. In this paper, we give a survey for MTL. First, we classify different MTL algorithms into several categories, including feature learning approach, low-rank approach, task clustering approach, task relation learning approach, and decomposition approach, and then discuss the characteristics of each approach. In order to improve the performance of learning tasks further, MTL can be combined with other learning paradigms including semi-supervised learning, active learning, unsupervised learning, reinforcement learning, multi-view learning and graphical models. When the number of tasks is large or the data dimensionality is high, batch MTL models are difficult to handle this situation and online, parallel and distributed MTL models as well as dimensionality reduction and feature hashing are reviewed to reveal their computational and storage advantages. Many real-world applications use MTL to boost their performance and we review representative works. Finally, we present theoretical analyses and discuss several future directions for MTL.

It seems like voice interfaces are going to be a big part of the future of computing; popping up in phones, smart speakers, and even household appliances. But how useful is this technology for people who don't communicate using speech? Are we creating a system that locks out certain users? These were the questions that inspired software developer Abhishek Singh to create a mod that lets Amazon's Alexa assistant understand some simple sign language commands. In a video, Singh demonstrates how the system works. An Amazon Echo is connected to a laptop, with a webcam (and some back-end machine learning software) decoding Singh's gestures in text and speech.