For months, the "first" AI art program, DALL-E, has been hidden behind a beta wall that has limited access. Now it's open to everyone to try out, with a generous amount of credits, to boot. Each signup adds 50 credits to your account, with each credit generating four 1024 1024 images from a single prompt from the OpenAI server. You'll get 15 new credits per month, though the credits do not roll over. OpenAI also has placed content limits on the type of images you can generate, forbidding violence, sexual acts (including nudity), politicians, and public figures.

Fran was a celebrity whale – the most photographed humpback in the San Francisco Bay, with 277 recorded sightings since 2005. Last month, she was hit by a ship and killed. Her death marked a grim milestone: Fran was the fifth whale to be killed by a ship strike in the area this year, according to the Marine Mammal Center. Collisions with ships are one of the leading causes of death for endangered whales, who breed, eat and travel in deep channels in the same busy waters that cargo ships frequent. Whales that spend their lives near the surface – such as humpbacks and right whales – are especially at risk. One 2019 study likened their plight to those of land animals forced to criss-cross the highways that cut through their habitats.

Speed-control forecasting, a challenging problem in driver behavior analysis, aims to predict the future actions of a driver in controlling vehicle speed such as braking or acceleration. In this paper, we try to address this challenge solely using egocentric video data, in contrast to the majority of works in the literature using either third-person view data or extra vehicle sensor data such as GPS, or both. To this end, we propose a novel graph convolutional network (GCN) based network, namely, EgoSpeed-Net. We are motivated by the fact that the position changes of objects over time can provide us very useful clues for forecasting the speed change in future. We first model the spatial relations among the objects from each class, frame by frame, using fully-connected graphs, on top of which GCNs are applied for feature extraction. Then we utilize a long short-term memory network to fuse such features per class over time into a vector, concatenate such vectors and forecast a speed-control action using a multilayer perceptron classifier. We conduct extensive experiments on the Honda Research Institute Driving Dataset and demonstrate the superior performance of EgoSpeed-Net.

Role requiring'No experience data provided' months of experience in None

Accurate traffic forecasting is vital to an intelligent transportation system. Although many deep learning models have achieved state-of-art performance for short-term traffic forecasting of up to 1 hour, long-term traffic forecasting that spans multiple hours remains a major challenge. Moreover, most of the existing deep learning traffic forecasting models are black box, presenting additional challenges related to explainability and interpretability. We develop Graph Pyramid Autoformer (X-GPA), an explainable attention-based spatial-temporal graph neural network that uses a novel pyramid autocorrelation attention mechanism. It enables learning from long temporal sequences on graphs and improves long-term traffic forecasting accuracy. Our model can achieve up to 35 % better long-term traffic forecast accuracy than that of several state-of-the-art methods. The attention-based scores from the X-GPA model provide spatial and temporal explanations based on the traffic dynamics, which change for normal vs. peak-hour traffic and weekday vs. weekend traffic.

Smartphones, like many consumer products, arrive in the US on giant container ships, vessels that are leading killers of endangered whales that play crucial roles in the climate and ocean health. Now a high-tech initiative called Whale Safe is detecting the huge marine mammals off the coast of San Francisco and alerting ship captains to slow down to avoid deadly collisions. Launched on Wednesday, Whale Safe aims to create "school zones" for imperiled blue whales, fin whales and humpback whales in busy shipping lanes, according to the project's managers at the Benioff Ocean Science Laboratory at the University of California at Santa Barbara and at the Bay Area's Marine Mammal Center. Speeders are caught by satellite surveillance and cited online. That gives consumers the opportunity to see, for instance, if that cruise they're contemplating is operated by a company with a history of ignoring sea speed limits.

Modal split prediction in transportation networks has the potential to support network operators in managing traffic congestion and improving transit service reliability. We focus on the problem of hourly prediction of the fraction of travelers choosing one mode of transportation over another using high-dimensional travel time data. We use logistic regression as base model and employ various regularization techniques for variable selection to prevent overfitting and resolve multicollinearity issues. Importantly, we interpret the prediction accuracy results with respect to the inherent variability of modal splits and travelers' aggregate responsiveness to changes in travel time. By visualizing model parameters, we conclude that the subset of segments found important for predictive accuracy changes from hour-to-hour and include segments that are topologically central and/or highly congested. We apply our approach to the San Francisco Bay Area freeway and rapid transit network and demonstrate superior prediction accuracy and interpretability of our method compared to pre-specified variable selection methods.

Whether it's playing tennis or writing an essay, most people have a preferred hand. Now, a study has shown that despite having eight arms to choose from, octopuses also have favourite appendages. Researchers from the University of Minnesota recorded octopuses attacking various prey, and found they preferred certain arms over others when hunting. The team hopes the findings could be used to develop next-generation, highly manipulative soft robots. 'If we can learn from octopuses, then we can apply that to making an underwater vehicle or soft robot application,' said Dr Trevor Wardill, an author of the study.

Smartphones, like many consumer products, arrive in the US on giant container ships, vessels that are leading killers of endangered whales that play crucial roles in the climate and ocean health. Now a high-tech initiative called Whale Safe is detecting the huge marine mammals off the coast of San Francisco and alerting ship captains to slow down to avoid deadly collisions. Launched on Wednesday, Whale Safe aims to create "school zones" for imperilled blue whales, fin whales and humpback whales in busy shipping lanes, according to the project's managers at the Benioff Ocean Science Laboratory at the University of California at Santa Barbara and at the Bay Area's Marine Mammal Center. Speeders are caught by satellite surveillance and cited online. That gives consumers the opportunity to see, for instance, if that cruise they're contemplating is operated by a company with a history of ignoring sea speed limits.

Predicting the traffic incident duration is a hard problem to solve due to the stochastic nature of incident occurrence in space and time, a lack of information at the beginning of a reported traffic disruption, and lack of advanced methods in transport engineering to derive insights from past accidents. This paper proposes a new fusion framework for predicting the incident duration from limited information by using an integration of machine learning with traffic flow/speed and incident description as features, encoded via several Deep Learning methods (ANN autoencoder and character-level LSTM-ANN sentiment classifier). The paper constructs a cross-disciplinary modelling approach in transport and data science. The approach improves the incident duration prediction accuracy over the top-performing ML models applied to baseline incident reports. Results show that our proposed method can improve the accuracy by $60\%$ when compared to standard linear or support vector regression models, and a further $7\%$ improvement with respect to the hybrid deep learning auto-encoded GBDT model which seems to outperform all other models. The application area is the city of San Francisco, rich in both traffic incident logs (Countrywide Traffic Accident Data set) and past historical traffic congestion information (5-minute precision measurements from Caltrans Performance Measurement System).