To survive in the dynamically-evolving world, we accumulate knowledge and improve our skills based on experience. In the process, gaining new knowledge does not disrupt our vigilance to external stimuli. In other words, our learning process is 'accumulative' and 'online' without interruption. However, despite the recent success, artificial neural networks (ANNs) must be trained offline, and they suffer catastrophic interference between old and new learning, indicating that ANNs' conventional learning algorithms may not be suitable for building intelligent agents comparable to our brain. In this study, we propose a novel neural network architecture (DynMat) consisting of dual learning systems, inspired by the complementary learning system (CLS) theory suggesting that the brain relies on short- and long-term learning systems to learn continuously. Our experiments show that 1) DynMat can learn a new class without catastrophic interference and 2) it does not strictly require offline training.

We consider peer review in a conference setting where there is typically an overlap between the set of reviewers and the set of authors. This overlap can incentivize strategic reviews to influence the final ranking of one's own papers. In this work, we address this problem through the lens of social choice, and present a theoretical framework for strategyproof and efficient peer review. We first present and analyze an algorithm for reviewer-assignment and aggregation that guarantees strategyproofness and a natural efficiency property called unanimity, when the authorship graph satisfies a simple property. Our algorithm is based on the so-called partitioning method, and can be thought as a generalization of this method to conference peer review settings. We then empirically show that the requisite property on the authorship graph is indeed satisfied in the ICLR-17 submission data, and further demonstrate a simple trick to make the partitioning method more practically appealing for conference peer review. Finally, we complement our positive results with negative theoretical results where we prove that under various ways of strengthening the requirements, it is impossible for any algorithm to be strategyproof and efficient.

A longstanding goal in character animation is to combine data-driven specification of behavior with a system that can execute a similar behavior in a physical simulation, thus enabling realistic responses to perturbations and environmental variation. We show that well-known reinforcement learning (RL) methods can be adapted to learn robust control policies capable of imitating a broad range of example motion clips, while also learning complex recoveries, adapting to changes in morphology, and accomplishing user-specified goals. Our method handles keyframed motions, highly-dynamic actions such as motion-captured flips and spins, and retargeted motions. By combining a motion-imitation objective with a task objective, we can train characters that react intelligently in interactive settings, e.g., by walking in a desired direction or throwing a ball at a user-specified target. This approach thus combines the convenience and motion quality of using motion clips to define the desired style and appearance, with the flexibility and generality afforded by RL methods and physics-based animation. We further explore a number of methods for integrating multiple clips into the learning process to develop multi-skilled agents capable of performing a rich repertoire of diverse skills. We demonstrate results using multiple characters (human, Atlas robot, bipedal dinosaur, dragon) and a large variety of skills, including locomotion, acrobatics, and martial arts.

A team of scientists at Universität Bonn in Germany has developed not-at-all-creepy software able to predict the future. However, before heading out for a lottery ticket, potential users should be aware that the software is currently at its best when predicting what a chef might be about to do or need when preparing a salad. The research is concerned with predicting actions, and the self-learning software is pretty good at it, once it's gone through a few hours of training videos. In this case, the software was fed 40 videos of around six minutes each in which different salad dishes were prepared consisting of an average of 20 actions. It also sat through 1,712 videos of 52 different actors making breakfast.

As humans, we've gotten pretty good at shaping the world around us. We can choose the molecular design of our fruits and vegetables, travel faster and further and stave off life threatening diseases with personalized medical care. However, what continues to elude our molding grasp is the airy notion of "time" – how to see further than our present moment, and ultimately how to make the most of it. As it turns out, robots might be the ones who can answer this question. Computer scientists from the University of Bonn in Germany wrote this week that they were able to design a software that could predict a sequence of events up to five minutes in the future with accuracy between 15 and 40 percent.

Artificial intelligence could be heading to Australian classrooms -- and in schools overseas, it's already there. In Bahia, Brazil, 15-year-old students David and Roama from Colegio Perfil often start their school day at home, or on the bus. They pick up their phones, log into the education app Geekie Lab, and begin their classes from wherever they are. "You can access it everywhere, as long as you have your phone with you," David said. Students from Colegio Perfil in Bahia use phones or computers to access the Geekie app.

Artificial intelligence is transforming the legal profession -- and that includes legal ethics. AI and similar cutting-edge technologies raise many complex ethical issues and challenges that lawyers ignore at their peril. At the same time, AI also holds out the promise of helping lawyers to meet their ethical obligations, serve their clients more effectively, and promote access to justice and the rule of law. What does AI mean for legal ethics, what should lawyers do to prepare for these changes, and how could AI help improve the legal profession? Together with our partners at Thomson Reuters, we at Above the Law have been examining these important subjects.

DISCOVERING and harnessing fire unlocked more nutrition from food, feeding the bigger brains and bodies that are the hallmarks of modern humans. Google's chief executive, Sundar Pichai, thinks his company's development of artificial intelligence trumps that. "AI is one of the most important things that humanity is working on," he told an event in California earlier this year. "It's more profound than, I don't know, electricity or fire." Hyperbolic analogies aside, Google's AI techniques are becoming more powerful and more important to its business.

Today, it is no longer a question of adopting AI or not. Instead, ask yourself if you and your sales team are ready for the inevitable. Artificial intelligence for business is a reality. If your goal is to forge ahead and lead in your field, then you need to adapt to a workplace where AI plays a crucial role. As J.J. Kardwell, founder and CEO of predictive marketing software company EverString, puts it: "Growth-focused sales organizations of every size and stage cannot afford to ignore the benefits of AI-assisted sales."

Reinforcement Learning (RL) refers to both the learning problem and the sub-field of machine learning which has lately been in the news for great reasons. RL based systems have now beaten world champions of Go, helped operate datacenters better and mastered a wide variety of Atari games. The research community is seeing many more promising results. With enough motivation, let us now take a look at the Reinforcement Learning problem. Reinforcement Learning is the most general description of the learning problem where the aim is to maximize a long-term objective.