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.
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.
A Georgia man was arrested Tuesday after he was driving 112 miles per hour. He told police he was speeding while using the video-sharing app Snapchat. Malon B. Neal, 24, was charged with speeding, reckless driving and using wireless communications while driving after an officer shooting radar saw Neal's 2015 black Dodge Charger change lanes and accelerate, according to local reports. Neal's car has been towed and he was released from custody. The driver told police he was going home after hanging out with a friend, adding that he was driving that fast "for Snapchat," reports AJC.com
Bing uses search, social, and other relevant data to make intelligent predictions about upcoming events, like sporting events, reality TV shows, award shows, and political elections. In this episode, Jennifer Marsman chats with Kushal Lakhotia and Walter Sun about the machine learning that powers Bing's predictions of who will win sporting matches like the NCAA March Madness tournament, the NBA playoffs, the NFL season, Wimbledon, the Cricket World Cup, the English Premier League, and more.