Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task on a network input to generate a network output. In one aspect, one of the systems includes a neural network configured to perform the machine learning task, the neural network including one or more expert neural network blocks that each include router that performs expert-choice routing between multiple expert neural networks.

Abstract: A crowd motion simulation method is provided based on real crowd motion videos. The method includes framing the videos and storing the framed videos into continuous high-definition images, generating a crowd density map of each image, and accurately positioning an individual in each density map to obtain the accurate position of each individual. The method also includes correlating the positions of each individual in different images to form a complete motion trajectory, and extracting motion trajectory data; and quantifying motion trajectory data, defining training data and data labels, and calculating data correlation. The method further includes building a deep convolutional neural network, and inputting the motion trajectory data for training to learn crowd motion behaviors; and randomly placing a plurality of simulation individuals in a two-dimensional space, testing a prediction effect of the deep convolutional neural network, adjusting parameters for simulation, and drawing a crowd motion trajectory.

Abstract: An example method includes providing, to a sequence model (i) a plurality of few-shot prompts, wherein each prompt comprises a demonstration passage, a demonstration task, and a demonstration query, wherein the demonstration task describes a type of retrieval, and wherein the demonstration query is relevant to the demonstration task, and (ii) a plurality of passages sampled from a corpus of passages. The method also includes receiving, from the sequence model and for the plurality of passages and based on the plurality of few-shot prompts, a respective plurality of predicted task-query pairs, the sequence model having been prompted to predict a task based on an input passage, and predict an output query relevant to the predicted task. The method further includes generating a synthetic training dataset comprising the plurality of passages and the respective plurality of predicted task-query pairs. The method also includes providing the synthetic training dataset.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task on an input to generate an output. In one aspect, one of the method includes receiving input data that describes an input of a machine learning task; receiving candidate output data that describes a set of candidate classification outputs of the machine learning task for the input; generating an input sequence that includes the input and the set of candidate classification outputs; processing the input sequence using a neural network to generate a network output that specifies a respective score for each candidate classification output in the set of candidate classification outputs; and generating an output of the machine learning task for the input, comprising selecting, as the output, a selected candidate classification output from the set of candidate classification outputs using the respective scores.

Abstract: A crowd motion simulation method is provided based on real crowd motion videos. The method includes framing the videos and storing the framed videos into continuous high-definition images, generating a crowd density map of each image, and accurately positioning an individual in each density map to obtain the accurate position of each individual. The method also includes correlating the positions of each individual in different images to form a complete motion trajectory, and extracting motion trajectory data; and quantifying motion trajectory data, defining training data and data labels, and calculating data correlation. The method further includes building a deep convolutional neural network, and inputting the motion trajectory data for training to learn crowd motion behaviors; and randomly placing a plurality of simulation individuals in a two-dimensional space, testing a prediction effect of the deep convolutional neural network, adjusting parameters for simulation, and drawing a crowd motion trajectory.