Neural Consciousness Flow Artificial Intelligence

The ability of reasoning beyond data fitting is substantial to deep learning systems in order to make a leap forward towards artificial general intelligence. A lot of efforts have been made to model neural-based reasoning as an iterative decision-making process based on recurrent networks and reinforcement learning. Instead, inspired by the consciousness prior proposed by Yoshua Bengio, we explore reasoning with the notion of attentive awareness from a cognitive perspective, and formulate it in the form of attentive message passing on graphs, called neural consciousness flow (NeuCFlow). Aiming to bridge the gap between deep learning systems and reasoning, we propose an attentive computation framework with a three-layer architecture, which consists of an unconsciousness flow layer, a consciousness flow layer, and an attention flow layer. We implement the NeuCFlow model with graph neural networks (GNNs) and conditional transition matrices. Our attentive computation greatly reduces the complexity of vanilla GNN-based methods, capable of running on large-scale graphs. We validate our model for knowledge graph reasoning by solving a series of knowledge base completion (KBC) tasks. The experimental results show NeuCFlow significantly outperforms previous state-of-the-art KBC methods, including the embedding-based and the path-based. The reproducible code can be found by the link below.

Algorithms (and gentlemen), start your engines!


On this Memorial Day weekend – traditional start of the racing season the US and the calendar home of the Indy 500 – we thought we'd take a look at the future of racing, and whether Ricky Bobby will find himself hammering it home in the driver's seat…or pushing fries in the concession stand. Racing leagues – including aptly-named Roborace – are popping up promising spectators the opportunity to see driverless cars compete in virtual battles of algorithms. Teams of researchers are taking algorithms similar to those already being used by major brands like Tesla and Google to put cars on the open road and put them to work on the racetrack. There is so much interest in the idea of pushing autonomous vehicle technologies to the extreme that track days have been set up to enable autonomous technologies developers to put their vehicles to he test on the track. Recently, Arrow Electronics broke records with its semi-autonomous vehicle at the Indianapolis Motor Speedway.

Optimal Data Collection For Informative Rankings Expose Well-Connected Graphs Machine Learning

Given a graph where vertices represent alternatives and arcs represent pairwise comparison data, the statistical ranking problem is to find a potential function, defined on the vertices, such that the gradient of the potential function agrees with the pairwise comparisons. Our goal in this paper is to develop a method for collecting data for which the least squares estimator for the ranking problem has maximal Fisher information. Our approach, based on experimental design, is to view data collection as a bi-level optimization problem where the inner problem is the ranking problem and the outer problem is to identify data which maximizes the informativeness of the ranking. Under certain assumptions, the data collection problem decouples, reducing to a problem of finding multigraphs with large algebraic connectivity. This reduction of the data collection problem to graph-theoretic questions is one of the primary contributions of this work. As an application, we study the Yahoo! Movie user rating dataset and demonstrate that the addition of a small number of well-chosen pairwise comparisons can significantly increase the Fisher informativeness of the ranking. As another application, we study the 2011-12 NCAA football schedule and propose schedules with the same number of games which are significantly more informative. Using spectral clustering methods to identify highly-connected communities within the division, we argue that the NCAA could improve its notoriously poor rankings by simply scheduling more out-of-conference games.

WWE Fastlane 2017: Predictions, Match Card For Final PPV Before WrestleMania 33

International Business Times

The final pay-per-view before WrestleMania 33 is set for Sunday night in Milwaukee with WWE Fastlane 2017. The show will have major implications for WWE's biggest PPV of the year as multiple titles could change hands. Kevin Owens has held the WWE Universal Championship for six months, but he's in danger of losing the belt to Goldberg. Goldberg hasn't held a title in more than 13 years, but his return to WWE has gone so well that he appears to be headed for another championship run. While that match could help set up the main event for WrestleMania 33, the WrestleMania 33 Raw Women's Championship Match at the April 2 PPV could also be established at WWE Fastlane.

LAO*, RLAO*, or BLAO*?

AAAI Conferences

In 2003, Bhuma and Goldsmith introduced a bidirectional variant of Hansen and Zilberstein's LAO* algorithm called BLAO* for solving goal-based MDPs. BLAO* consistently ran faster than LAO* on the racetrack examples used in Hansen and Zilberstein's paper. In this paper, we analyze the performance of BLAO* in comparison with both LAO* and our newly proposed algorithm, RLAO*, the reverse LAO* search, to understand what makes the bidirectional search work well.