A state-of-the-art criterion to evaluate the importance of a given learned clause is called Literal Block Distance (LBD) score. It measures the number of distinct decision levels in a given learned clause. The lower the LBD score of a learned clause, the better is its quality. The learned clauses with LBD score of 2, called glue clauses, are known to possess high pruning power which are never deleted from the clause databases of the modern CDCL SAT solvers. In this work, we relate glue clauses to decision variables. We call the variables that appeared in at least one glue clause up to the current search state Glue Variables. We first show experimentally, by running the state-of-the-art CDCL SAT solver MapleLCMDist on benchmarks from SAT Competition-2017 and 2018, that branching decisions with glue variables are categorically more inference and conflict efficient than nonglue variables. Based on this observation, we develop a structure aware CDCL variable bumping scheme, which bumps the activity score of a glue variable based on its appearance count in the glue clauses that are learned so far by the search. Empirical evaluation shows effectiveness of the new method over the main track instances from SAT Competition 2017 and 2018.

Fast and efficient path generation is critical for robots operating in complex environments. This motion planning problem is often performed in a robot's actuation or configuration space, where popular pathfinding methods such as A*, RRT*, get exponentially more computationally expensive to execute as the dimensionality increases or the spaces become more cluttered and complex. On the other hand, if one were to save the entire set of paths connecting all pair of locations in the configuration space a priori, one would run out of memory very quickly. In this work, we introduce a novel way of producing fast and optimal motion plans for static environments by using a stepping neural network approach, called OracleNet. OracleNet uses Recurrent Neural Networks to determine end-to-end trajectories in an iterative manner that implicitly generates optimal motion plans with minimal loss in performance in a compact form. The algorithm is straightforward in implementation while consistently generating near-optimal paths in a single, iterative, end-to-end roll-out. In practice, OracleNet generally has fixed-time execution regardless of the configuration space complexity while outperforming popular pathfinding algorithms in complex environments and higher dimensions

Parking pressure has been steadily increasing in cities as well as in university and corporate campuses. To relieve this pressure, this paper studies a car-pooling platform that would match riders and drivers, while guaranteeing a ride back and exploiting spatial and temporal locality. In particular, the paper formalizes the Commute Trip Sharing Problem (CTSP) to find a routing plan that maximizes ride sharing for a set of commute trips. The CTSP is a generalization of the vehicle routing problem with routes that satisfy time window, capacity, pairing, precedence, ride duration, and driver constraints. The paper introduces two exact algorithms for the CTPS: A route-enumeration algorithm and a branch-and-price algorithm. Experimental results show that, on a high-fidelity, real-world dataset of commute trips from a mid-size city, both algorithms optimally solve small and medium-sized problems and produce high-quality solutions for larger problem instances. The results show that car pooling, if widely adopted, has the potential to reduce vehicle usage by up to 57% and decrease vehicle miles traveled by up to 46% while only incurring a 22% increase in average ride time per commuter for the trips considered.

Weather Recognition plays an important role in our daily lives and many computer vision applications. However, recognizing the weather conditions from a single image remains challenging and has not been studied thoroughly. Generally, most previous works treat weather recognition as a single-label classification task, namely, determining whether an image belongs to a specific weather class or not. This treatment is not always appropriate, since more than one weather conditions may appear simultaneously in a single image. To address this problem, we make the first attempt to view weather recognition as a multi-label classification task, i.e., assigning an image more than one labels according to the displayed weather conditions. Specifically, a CNN-RNN based multi-label classification approach is proposed in this paper. The convolutional neural network (CNN) is extended with a channel-wise attention model to extract the most correlated visual features. The Recurrent Neural Network (RNN) further processes the features and excavates the dependencies among weather classes. Finally, the weather labels are predicted step by step. Besides, we construct two datasets for the weather recognition task and explore the relationships among different weather conditions. Experimental results demonstrate the superiority and effectiveness of the proposed approach. The new constructed datasets will be available at https://github.com/wzgwzg/Multi-Label-Weather-Recognition.

Continual learning aims to enable machine learning models to learn a general solution space for past and future tasks in a sequential manner. Conventional models tend to forget the knowledge of previous tasks while learning a new task, a phenomenon known as catastrophic forgetting. When using Bayesian models in continual learning, knowledge from previous tasks can be retained in two ways: (i) posterior distributions over the parameters, containing the knowledge gained from inference in previous tasks, which then serve as the priors for the following task; (ii) coresets, containing knowledge of data distributions of previous tasks. Here, we show that Bayesian continual learning can be facilitated in terms of these two means through the use of natural gradients and Stein gradients respectively.

Quantum tomography is currently ubiquitous for testing any implementation of a quantum information processing device. Various sophisticated procedures for state and process reconstruction from measured data are well developed and benefit from precise knowledge of the model describing state preparation and the measurement apparatus. However, physical models suffer from intrinsic limitations as actual measurement operators and trial states cannot be known precisely. This scenario inevitably leads to state-preparation-and-measurement (SPAM) errors degrading reconstruction performance. Here we develop and experimentally implement a machine learning based protocol reducing SPAM errors. We trained a supervised neural network to filter the experimental data and hence uncovered salient patterns that characterize the measurement probabilities for the original state and the ideal experimental apparatus free from SPAM errors. We compared the neural network state reconstruction protocol with a protocol treating SPAM errors by process tomography, as well as to a SPAM-agnostic protocol with idealized measurements. The average reconstruction fidelity is shown to be enhanced by 10\% and 27\%, respectively. The presented methods apply to the vast range of quantum experiments which rely on tomography.

On a recent Tuesday evening, the experimental musician Julianna Barwick checked into Sister City, a new two-hundred-room boutique hotel on the Lower East Side of Manhattan. If you're having the sort of day that makes you want to minimize human interaction, Sister City is a merciful oasis: there are self-service registration kiosks in the lobby, and each floor features a supply closet containing the sorts of sundries that you'd usually have to request from the concierge. The lobby has sparse but careful décor--clean white walls, cherry-wood furniture, floor tiles in muted shades of green and gray--suggesting a Scandinavian sauna, or perhaps the careful serenity of a Japanese stationery store; the vibe is "Serenity Now!" filtered through Instagram. Barwick, who has long, dark hair and inquisitive eyes, is using the sky immediately above the hotel as a source for a new composition. A camera mounted to the roof of the building sends information about the goings-on in the airspace above the hotel (rain, clouds, pigeons, airplanes, wind, sun, moonlight, drones, helicopters, constellations, what have you) to Pereira's program, which uses Microsoft's artificial intelligence to cue sounds written and recorded by Barwick.

Tesla has sent a team to investigate a video on Chinese social media which showed a parked Tesla Model S car exploding, the latest in a string of fire incidents involving the company's cars. The video, time stamped Sunday evening and widely shared on China's Twitter-like Weibo, shows the parked EV emit smoke and burst into flames seconds later. A video purportedly of the aftermath showed a line of three cars completely destroyed. The video comes as Tesla is preparing to unveil its "full self-driving" tech at a conference in Palo Alto, California, on Monday. The video is likely to overshadow the company's unveiling of its latest autonomous driving software and hardware.

Shot at the New York Auto Show, the new Cadillac Super Cruise includes a driver facing camera. In 2018, drivers asked for hi-tech, onboard cameras and now they're getting them. The New York International Auto Show, open to the public through April 28, is ground zero for next-generation car technology and also home to several vehicles that offer in-car and exterior monitoring systems. From upgraded blind spot cams to facial recognition software installed in the dash, cars on display are equipped with several sets of digital eyes that can improve vehicle security, safety and convenience. Some of the cameras can help propel cars closer toward an autonomous future by enabling the vehicle to see what's around it.

SAN FRANCISCO - Chief Executive Elon Musk said Tesla Inc. "robotaxis" with no human drivers will be available in some markets next year thanks to exponential improvements in technology. "Probably two years from now we'll make a car with no steering wheels or pedals," he predicted, while acknowledging he often misses deadlines and his presentation on Monday started 30 minutes late. Musk also unveiled on Monday a microchip for self-driving vehicles that the electric car company hopes will give Tesla an edge over rivals and persuade investors its massive investment in autonomous driving will pay off. The presentation came two days before Tesla is expected to announce a quarterly loss on fewer deliveries of its Model 3 sedan, which represents Tesla's attempt to become a volume carmaker. Global carmakers, large technology companies and an array of startups are developing self-driving cars -- including Alphabet Inc.'s Waymo and Uber Technologies Inc. -- but experts say it will be years before the systems are ready for prime time.