Despite recent advances in hardware acceleration of ray tracing, real-time ray budgets remain stubbornly limited at a handful of samples per pixel (spp) on commodity hardware, placing the onus on denoising algorithms to achieve high visual quality for path traced global illumination. Neural network-based solutions give excellent result quality at the cost of increased execution time relative to hand-engineered methods, making them less suitable for deployment on resource-constrained systems. We therefore propose incorporating a neural network into a computationally-efficient local linear model-based denoiser, and demonstrate faithful single-frame reconstruction of global illumination for Lambertian scenes at very low sample counts (1spp) and for low computational cost. Other contributions include improving the quality and performance of local linear model-based denoising through a simplified mathematical treatment, and demonstration of the surprising usefulness of ambient occlusion as a guide channel. We also show how our technique is straightforwardly extensible to joint denoising and upsampling of path traced renders with reference to low-cost, rasterized guide channels.

Plan Jericho has introduced Ai-Search – an artificial intelligence (Ai) prototype – to transform airborne search and rescue. The prototype came about after Air Commodore Darren Goldie challenged Jericho to find a way of using a detector on an aircraft to enhance search and rescue (SAR). Plan Jericho's Ai lead Wing Commander Michael Gan said Jericho saw the opportunity to use Ai to augment and enhance SAR. "The idea was to train a machine-learning algorithm and Ai sensors to complement existing visual search techniques. Our vision was to give any aircraft and other Defence platforms, including unmanned aerial systems, a low-cost, improvised SAR capability," Wing Commander Gan said.

From IT to marketing to HR, artificial intelligence (AI) is making its way throughout the enterprise. For security professionals, learning about the technology and how to apply it can be critical for keeping up with malicious actors and turning security into an asset. The question is how to do so without creating a new section on the "expense" side of the ledger. The good news: Tools are available that allow virtually anyone with basic software development skills to begin honing their AI chops for a price that ranges from free to a few hundred dollars. AI security involves many areas of research, says Jason Mancuso, a research scientist at Dropout Labs who spoke at the AI Village at DEF CON.

It seems like every day brings news of some new artificial intelligence (AI) application and/or deployment. In many cases -- like the Amazon Echo or Google Home -- the AI part of the system is performed in the cloud. When I say, "Alexa, turn the Prognostication Engine on," for example, although echo cancellation, noise reduction, and other pre-processing tasks are performed locally, the decoding of my speech by Alexa to decide what I'm waffling on about in order to perform the desired action -- which is to control one of my iClever smart plugs in this example (see "Limping Into the 21st Century with Smart Technology") -- is performed in the cloud on Amazon's servers. As an aside, I'd love to be able to say, "Alexa, activate the Prognostication Engine," but I don't know how to get her to understand that "activate" and "turn on" mean the same thing. In other cases, the AI is performed on a handheld device like a smartphone or tablet, like the multi-layered neural networks employed by the MyScript Nebo application running on my iPad Pro, for example (see "Artificial Intelligence-Based Handwriting Recognition").

The design and implementation of a robotic chess agent is described. Shallow Blue, a competitor in the AAAI 2011 Small Scale Manipulation Challenge, is constructed with low-cost components including Lego NXT bricks and is programmed using Java and Lejos.

Machine learning techniques are gaining prevalence in the production of a wide range of classifiers for complex real-world applications with nonuniform testing and misclassification costs. The increasing complexity of these applications poses a real challenge to resource management during learning and classification. In this work we introduce ACT (anytime cost-sensitive tree learner), a novel framework for operating in such complex environments. ACT is an anytime algorithm that allows learning time to be increased in return for lower classification costs. It builds a tree top-down and exploits additional time resources to obtain better estimations for the utility of the different candidate splits. Using sampling techniques, ACT approximates the cost of the subtree under each candidate split and favors the one with a minimal cost. As a stochastic algorithm, ACT is expected to be able to escape local minima, into which greedy methods may be trapped. Experiments with a variety of datasets were conducted to compare ACT to the state-of-the-art cost-sensitive tree learners. The results show that for the majority of domains ACT produces significantly less costly trees. ACT also exhibits good anytime behavior with diminishing returns.