Every year, we are confronted with new facts and scenarios emerging out of climate change and global warming, each more terrifying and apocalyptic than the last. In fact, several well-known scientists and tech moguls have made predictions regarding them. Prominent linguist and public intellectual Noam Chomsky said last year that the COP22 Marrakech climate summit in Morocco, which began on Nov. 7, "basically ceased" to function on Nov.9 after the delegates were confronted with the news that Donald Trump was elected as the next U.S. president. Speaking to over 2,000 people at Riverside Church on Dec. 5, Chomsky also made several related climate change predictions. "The question that was left was whether it would be possible to carry forward this global effort to deal with the highly critical problem of environmental catastrophe, if the leader of the free world, the richest and most powerful country in history, would pull out completely, as appeared to be the case," Chomsky said.

Effortless customer engagement is top of mind for Quinn Banks, senior product marketing manager at Farmers Insurance -- and he's spearheading the implementation of machine learning to get the company there. "We are working with machine learning to make our app more efficient when customers come in, or even to anticipate what a customer will need when they come into the application, based on their habits, their environmental changes, even Read More ... Tags: Corporate Enterprises Computer systems Customers Artificial intelligence Machine intelligence Machine learning Google crams machine learning into smartwatches in A.I. push Google is bringing artificial intelligence to a whole new set of devices, including Android Wear 2.0 smartwatches and the Raspberry Pi board, later this year. These devices don't require a set of powerful CPUs and GPUs to carry out machine-learning tasks. Google researchers are instead trying to lighten the hardware load to carry out basic A.I. tasks, as exhibited by last week's release of the Android Wear 2.0 operating system Read More ... Tags: Smart Devices Computer systems Smart Watches Artificial intelligence Machine intelligence Machine learning Wearable devices In this video from the 2017 HPC Advisory Council Stanford Conference, DK Panda presents: Best Practices: Designing HPC & Deep Learning Middleware for Exascale Systems. "This talk will focus on challenges in designing runtime environments for exascale systems with millions of processors and accelerators to support various programming models.

Chichewa (also Chewa and Nyanja) is a Bantu language of about 12 Million speakers, spoken mostly in Malawi and around. Lines 216-221 have the code commented out that enable it to be run from command line instead of via a web form. The parser implements the description of Chichewa affixes outline in: Mchombo, Sam, (2004). Cambridge Syntax Guides Page references in the comments of the code are references to pages in this text. The parser was used as part of my PhD, so you can use this citation if you want to reference the code in a publication: Munro, Robert (2012). It was built to compare a hand-crafted parser with morphological parsers that learned using superivsed and unsupervised machine learning.

Monte Carlo Tree Search (MCTS) is a family of directed search algorithms that has gained widespread attention in recent years. Despite the vast amount of research into MCTS, the effect of modifications on the algorithm, as well as the manner in which it performs in various domains, is still not yet fully known. In particular, the effect of using knowledge-heavy rollouts in MCTS still remains poorly understood, with surprising results demonstrating that better-informed rollouts often result in worse-performing agents. We present experimental evidence suggesting that, under certain smoothness conditions, uniformly random simulation policies preserve the ordering over action preferences. This explains the success of MCTS despite its common use of these rollouts to evaluate states. We further analyse non-uniformly random rollout policies and describe conditions under which they offer improved performance.

Estimating the joint probability density function of a dataset is a central task in many machine learning applications. In this work we address the fundamental problem of kernel bandwidth estimation for variable kernel density estimation in high-dimensional feature spaces. We derive a variable kernel bandwidth estimator by minimizing the leave-one-out entropy objective function and show that this estimator is capable of performing estimation in high-dimensional feature spaces with great success. We compare the performance of this estimator to state-of-the art maximum-likelihood estimators on a number of representative high-dimensional machine learning tasks and show that the newly introduced minimum leave-one-out entropy estimator performs optimally on a number of high-dimensional datasets considered.

Inference from an observed or hypothesized condition to a plausible cause or explanation for this condition is known as abduction. For many tasks, the acquisition of the necessary knowledge by machine learning has been widely found to be highly effective. However, the semantics of learned knowledge are weaker than the usual classical semantics, and this necessitates new formulations of many tasks. We focus on a recently introduced formulation of the abductive inference task that is thus adapted to the semantics of machine learning. A key problem is that we cannot expect that our causes or explanations will be perfect, and they must tolerate some error due to the world being more complicated than our formalization allows. This is a version of the qualification problem, and in machine learning, this is known as agnostic learning. In the work by Juba that introduced the task of learning to make abductive inferences, an algorithm is given for producing k-DNF explanations that tolerates such exceptions: if the best possible k-DNF explanation fails to justify the condition with probability ε, then the algorithm is promised to find a k-DNF explanation that fails to justify the condition with probability at most O(nkε), where n is the number of propositional attributes used to describe the domain. Here, we present an improved algorithm for this task. When the best k- DNF fails with probability ε, our algorithm finds a k-DNF that fails with probability at most O ̃(nk/2ε) (i.e., suppressing logarithmic factors in n and 1/ε). We also examine the empirical advantage of this new algorithm over the previous algorithm in two test domains, one of explaining conditions generated by a “noisy” k-DNF rule, and another of explaining conditions that are actually generated by a linear threshold rule.

From Google's self-driving cars to Amazon's purchase predictions, artificial intelligence (AI) is any program that does something we would normally consider an intelligent human act. But as AI technology continues to develop rapidly, prominent personalities including Stephen Hawking and Bill Gates have voiced their concern about the rise of super-intelligent machines. They question they ask is: "How dangerous could AI become?" We've all watched at least one science fiction movie where an intelligent robot goes rogue and tries to destroy all humanity. And while we certainly aren't ignoring the valid concerns raised about super-intelligent machines, it is possible that AI and humans can be complementary.

Banks around the world are being confronted with a record number of regulations, and those falling short of institutional obligations are paying a high price for their errors. In response, major financial institutions are grasping big data solutions in a bid to comply with often dense regulations and reduce regulatory breaches. "Considering many banks have grown organically, often via merger and acquisition, their data is not always consistent and well organised," according to James Arnett, a partner at business and technology consulting firm Capco. Mr Arnett believes that new tools can be created through the application of data analytics, which will transform banks compliance programmes from manual, non-scalable projects into lower-cost and automated processes. "There is a real opportunity for banking clients to embrace data analytics to answer the underlying theme of regulation strategically rather than to treat each regulation as a'tick-the-box' exercise," he says.

Science council moves to safeguard South Africa's robotics prowess Since Czech playwright Karel Capek popularised and, indeed, named the concept of the robot in his 1920 science-fiction play, RUR (Rossum's Universal Robots) – the word is derived from the Czech word'robota', which means labour – it has exerted a fascination on both the popular and the scientific, and on engineering and technological minds. The robot quickly became a mainstay of science fiction, sometimes benign (as with Robby the Robot in the film Forbidden Planet or R2D2 and C3PO from the Star Wars series), sometimes hostile. The first real working robot, however, bore no resemblance to the humanoid robots beloved of science fiction. This was Unimate, developed by the Unimation (Universal Automation) company in the US, which was specifically founded to manufacture robots for industry. Unimate, which entered service on a General Motors assembly line in 1961, was the forerunner of all today's industrial robots and, being in the form of a large mechanical arm, also set the format most such robots still follow.

Antipoaching patrols like this team at the Lewa Wildlife Conservancy in Kenya may soon use AI technology to stay one step ahead of criminals. Poachers kill an estimated 96 African elephants every day, causing conservationists to warn that the iconic animals could disappear in our lifetime if the tide doesn't turn. But now scientists hope a new artificial intelligence (AI) tool could help wildlife officials get a leg up against poachers. PAWS, which stands for Protection Assistant for Wildlife Security, is a newly developed AI that takes data about previous poaching activities and outputs routes for patrols based on where poaching is likely to occur. These routes are also randomized to keep poachers from learning patrol patterns.