Z Advanced Computing, Inc. (ZAC) of Potomac, MD announced on August 27 that it is funded by the US Air Force, to use ZAC's detailed 3D image recognition technology, based on Explainable-AI, for drones (unmanned aerial vehicle or UAV) for aerial image/object recognition. ZAC is the first to demonstrate Explainable-AI, where various attributes and details of 3D (three dimensional) objects can be recognized from any view or angle. "With our superior approach, complex 3D objects can be recognized from any direction, using only a small number of training samples," said Dr. Saied Tadayon, CTO of ZAC. "For complex tasks, such as drone vision, you need ZAC's superior technology to handle detailed 3D image recognition." "You cannot do this with the other techniques, such as Deep Convolutional Neural Networks, even with an extremely large number of training samples. That's basically hitting the limits of the CNNs," continued Dr. Bijan Tadayon, CEO of ZAC.

Guez, Arthur, Silver, David, Dayan, Peter

Bayesian model-based reinforcement learning is a formally elegant approach to learning optimal behaviour under model uncertainty, trading off exploration and exploitation in an ideal way. Unfortunately, finding the resulting Bayes-optimal policies is notoriously taxing, since the search space becomes enormous. In this paper we introduce a tractable, sample-based method for approximate Bayes-optimal planning which exploits Monte-Carlo tree search. Our approach outperformed prior Bayesian model-based RL algorithms by a significant margin on several well-known benchmark problems -- because it avoids expensive applications of Bayes rule within the search tree by lazily sampling models from the current beliefs. We illustrate the advantages of our approach by showing it working in an infinite state space domain which is qualitatively out of reach of almost all previous work in Bayesian exploration.

We extend the Chow-Liu algorithm for general random variables while the previous versions only considered finite cases. In particular, this paper applies the generalization to Suzuki's learning algorithm that generates from data forests rather than trees based on the minimum description length by balancing the fitness of the data to the forest and the simplicity of the forest. As a result, we successfully obtain an algorithm when both of the Gaussian and finite random variables are present.

Kemp, Charles, Goodman, Noah, Tenenbaum, Joshua B.

Much of human knowledge is organized into sophisticated systems that are often called intuitive theories. We propose that intuitive theories are mentally represented ina logical language, and that the subjective complexity of a theory is determined by the length of its representation in this language. This complexity measure helps to explain how theories are learned from relational data, and how they support inductive inferences about unobserved relations. We describe two experiments that test our approach, and show that it provides a better account of human learning and reasoning than an approach developed by Goodman [1]. What is a theory, and what makes one theory better than another?

Many real-world problems, including inference in Bayes Nets, can be reduced to #SAT, the problem of counting the number of models of a propositional theory. This has motivated the need for efficient #SAT solvers. Currently, such solvers utilize a modified version of DPLL that employs decomposition and caching, techniques that significantly increase the time it takes to process each node in the search space. In addition, the search space is significantly larger than when solving SAT since we must continue searching even after the first solution has been found. It has previously been demonstrated that the size of a DPLL search tree can be significantly reduced by doing more reasoning at each node. However, for SAT the reductions gained are often not worth the extra time required. In this paper we verify the hypothesis that for #SAT this balance changes. In particular, we show that additional reasoning can reduce the size of a #SAT solver's search space, that this reduction cannot always be achieved by the already utilized technique of clause learning, and that this additional reasoning can be cost effective.