Many believed an algorithm would transcend humanity with cognitive awareness. Machines would discern and learn tasks without human intervention and replace workers in droves. They quite literally would be able to "think". Many people even raised the question whether we could have robots for spouses. But I am not talking about today.

There are several different ways to play the game, but in esports the most common is a 1v1 tournament played over five games. To start, a player must choose to play one of three different alien "races" - Zerg, Protoss or Terran, all of which have distinctive characteristics and abilities (although professional players tend to specialise in one race). Each player starts with a number of worker units, which gather basic resources to build more units and structures and create new technologies. These in turn allow a player to harvest other resources, build more sophisticated bases and structures, and develop new capabilities that can be used to outwit the opponent. To win, a player must carefully balance big-picture management of their economy - known as macro - along with low-level control of their individual units - known as micro.

Since its founding, the Defense Advanced Research Projects Agency (DARPA) has been a hub of innovation. While created as the research arm of the Department of Defense, DARPA has played an important role in some of the technologies that have become (or will become) fundamental to modern human societies. In the 1960s and 1970s, DARPA (then known as ARPA), created ARPANET, the computer network that became the precursor to the internet. In 2003, DARP launched CALO, a project that ushered in the era of Siri and other voice-enabled assistants. In 2004, DARPA launched the Grand Challenge, a competition that set the stage for current developments and advances in self-driving cars. In 2013, DARPA launched the Brain Initiative, an ambitious project that brings together universities, tech companies and neuroscientists to discover how the brain works and develop technologies that enable the human brain to interact with the digital world. Among DARPA's many exciting projects is Explainable Artificial Intelligence (XAI), an initiative launched in 2016 aimed at solving one of the principal challenges of deep learning and neural networks, the subset of AI that is becoming increasing prominent in many different sectors.

It may seem like artificial intelligence is on a path to rule the world, but there's still a flicker of hope for humans. In December, Google's DeepMind AI program called AlphaStar played a series of StarCraft II matches against two human players, though the results weren't revealed until Thursday. While the AI won ten games, signaling that the robot overlords are still on a quest to take over, one of the professional human players still managed to squeak out a single win in his match-up against the computer. This is it, ladies and gentlemen! For the first time in history a pro concedes to an Artificial Intelligence!

Since the breakthrough of machine learning by convolutional deep neural network in 2012, a lot of new activities to utilize these new fruits has been in boom, and AI research center (AIRC) under AIST has been promoting significant research activities and obtained various kinds of excellent results. Now, the AI research and development will be in the new phase where concrete results are now exploited in the variety kind of business activities, and new type of advanced research topics begins to be studied globally. AIRC continuously keep its focus on AI embedded in the real world, and wish to lead this new era of research and development AI. In order to realize this wish, the international symposium will be held on 21st of February.

AI agents developed by Google's DeepMind subsidiary have beaten human pros at Starcraft II -- a first in the world of artificial intelligence. In a series of matches streamed on YouTube and Twitch, AI players beat the humans 10 games in a row. In the final match, pro player Grzegorz "MaNa" Komincz was able to snatch a single victory for humanity. "The history of AI has been marked by a number of significant benchmark victories in different games," David Silver, DeepMind's research co-lead, said after the matches. "And I hope -- though there's clearly work to do -- that people in the future may look back at [today] and perhaps consider this as another step forward for what AI systems can do."

The estimation of unknown values of parameters (or hidden variables, control variables) that characterise a physical system often relies on the comparison of measured data with synthetic data produced by some numerical simulator of the system as the parameter values are varied. This process often encounters two major difficulties: the generation of synthetic data for each considered set of parameter values can be computationally expensive if the system model is complicated; and the exploration of the parameter space can be inefficient and/or incomplete, a typical example being when the exploration becomes trapped in a local optimum of the objection function that characterises the mismatch between the measured and synthetic data. A method to address both these issues is presented, whereby: a surrogate model (or proxy), which emulates the computationally expensive system simulator, is constructed using deep recurrent networks (DRN); and a nested sampling (NS) algorithm is employed to perform efficient and robust exploration of the parameter space. The analysis is performed in a Bayesian context, in which the samples characterise the full joint posterior distribution of the parameters, from which parameter estimates and uncertainties are easily derived. The proposed approach is compared with conventional methods in some numerical examples, for which the results demonstrate that one can accelerate the parameter estimation process by at least an order of magnitude.

Adaptive methods such as Adam and RMSProp are widely used in deep learning but are not well understood. In this paper, we seek a crisp, clean and precise characterization of their behavior in nonconvex settings. To this end, we first provide a novel view of adaptive methods as preconditioned SGD, where the preconditioner is estimated in an online manner. By studying the preconditioner on its own, we elucidate its purpose: it rescales the stochastic gradient noise to be isotropic near stationary points, which helps escape saddle points. Furthermore, we show that adaptive methods can efficiently estimate the aforementioned preconditioner. By gluing together these two components, we provide the first (to our knowledge) second-order convergence result for any adaptive method. The key insight from our analysis is that, compared to SGD, adaptive methods escape saddle points faster, and can converge faster overall to second-order stationary points.

In this work, we introduce a novel framework that employs cluster annotation to boost active learning by reducing the number of human interactions required to train deep neural networks. Instead of annotating single samples individually, humans can also label clusters, producing a higher number of annotated samples with the cost of a small label error. Our experiments show that the proposed framework requires 82% and 87% less human interactions for CIFAR-10 and EuroSAT datasets respectively when compared with the fully-supervised training while maintaining similar performance on the test set.

It is well-known that the expressivity of a neural network depends on its architecture, with deeper networks expressing more complex functions. In the case of networks that compute piecewise linear functions, such as those with ReLU activation, the number of distinct linear regions is a natural measure of expressivity. It is possible to construct networks for which the number of linear regions grows exponentially with depth, or with merely a single region; it is not clear where within this range most networks fall in practice, either before or after training. In this paper, we provide a mathematical framework to count the number of linear regions of a piecewise linear network and measure the volume of the boundaries between these regions. In particular, we prove that for networks at initialization, the average number of regions along any one-dimensional subspace grows linearly in the total number of neurons, far below the exponential upper bound. We also find that the average distance to the nearest region boundary at initialization scales like the inverse of the number of neurons. Our theory suggests that, even after training, the number of linear regions is far below exponential, an intuition that matches our empirical observations. We conclude that the practical expressivity of neural networks is likely far below that of the theoretical maximum, and that this gap can be quantified.