Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting intermediate reinforcement learning goals. One of the methods includes obtaining a plurality of demonstration sequences, each of the demonstration sequences being a sequence of images of an environment while a respective instance of a reinforcement learning task is being performed; for each demonstration sequence, processing each image in the demonstration sequence through an image processing neural network to determine feature values for a respective set of features for the image; determining, from the demonstration sequences, a partitioning of the reinforcement learning task into a plurality of subtasks, wherein each image in each demonstration sequence is assigned to a respective subtask of the plurality of subtasks; and determining, from the feature values for the images in the demonstration sequences, a respective set of discriminative features for each of the plurality of subtasks.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting intermediate reinforcement learning goals. One of the methods includes obtaining a plurality of demonstration sequences, each of the demonstration sequences being a sequence of images of an environment while a respective instance of a reinforcement learning task is being performed; for each demonstration sequence, processing each image in the demonstration sequence through an image processing neural network to determine feature values for a respective set of features for the image; determining, from the demonstration sequences, a partitioning of the reinforcement learning task into a plurality of subtasks, wherein each image in each demonstration sequence is assigned to a respective subtask of the plurality of subtasks; and determining, from the feature values for the images in the demonstration sequences, a respective set of discriminative features for each of the plurality of subtasks.

The present disclosure provides systems and methods for predicting a disease state of a subject using ultrasound imaging and ancillary information to the ultrasound imaging. At least two quantitative measurements of a subject, including at least one measurement taken using ultrasound imaging, as part of quantified information can be identified. One of the quantitative measurements can be compared to a first predetermined standard, included as part of ancillary information to the quantified information, in order to identify a first initial value. Further, another of the quantitative measurements can be compared to a second predetermined standard, included as part of the ancillary information, in order to identify a second initial value. Subsequently, the quantitative information can be correlated with the ancillary information using the first initial value and the second initial value to determine a final value that is predictive of a disease state of the subject.

Embodiments of the present application provide a method and a device for optimizing a target operation speed curve in an ATO of a train. The method includes: calculating a plurality of performance indexes of the train driving in a current section of a line, and constructing an objective function for optimizing the target operation speed curve of the train according to the plurality of performance indexes; determining constraint conditions of the objective function according to speed limit information of the line and running time of the train in the current section; and solving the objective function according to the constraint conditions based on a differential evolution algorithm to obtain the target operation speed curve of the train. The objective function for optimizing the target operation speed curve of the train are constructed using the plurality of performance indexes, which makes the optimization of the train speed curve more accurate.

Embodiments of the present application provide a method and a device for optimizing a target operation speed curve in an ATO of a train. The method includes: calculating a plurality of performance indexes of the train driving in a current section of a line, and constructing an objective function for optimizing the target operation speed curve of the train according to the plurality of performance indexes; determining constraint conditions of the objective function according to speed limit information of the line and running time of the train in the current section; and solving the objective function according to the constraint conditions based on a differential evolution algorithm to obtain the target operation speed curve of the train. The objective function for optimizing the target operation speed curve of the train are constructed using the plurality of performance indexes, which makes the optimization of the train speed curve more accurate.

A method includes generating first contrast significance data for a first computer vision model generated from a first training set of medical scans. First significant contrast parameters are identified based on the first contrast significance data. A first re-contrasted training set is generated based on performing a first intensity transformation function on the first training set of medical scans, where the first intensity transformation function utilizes the first significant contrast parameters. A first re-trained model is generated from the first re-contrasted training set, which is associated with corresponding output labels based on abnormality data for the first training set of medical scans. Re-contrasted image data of a new medical scan is generated based on performing the first intensity transformation function. Inference data indicating at least one abnormality detected in the new medical scan is generated based on utilizing the first re-trained model on the re-contrasted image data.

The evolutionary feature selection algorithm is combined with model evaluation during training to learn feature subsets that maximize speech/non-speech distribution distances. The technique enables ensembling of low-cost models over similar features subspaces increases classification accuracy and has similar computational complexity in practice. Prior to training the models, feature analysis is conducted via an evolutionary feature selection algorithm which measures fitness for each feature subset in the population by its k-fold cross validation score. PCA and LDA based eigen-features are computed for each subset and fitted with a Gaussian Mixture Model from which combinations of feature subsets with Maximum Mean Discrepancy scores are obtained. During inference, the resulting features are extracted from the input signal and given as input to the trained neural networks.

The disclosure provides an objective identification device, comprising: a classifier training circuit configured to extract objective characteristics based on training samples and perform offline training based on the objective characteristics to obtain a classifier; and a calculation circuit is configured to identify an objective in an image based on a particle swarm optimization algorithm, wherein each of particles is defined as an object having a predefined size in the image; and a fitness value of each of particles is calculated based on the classifier and the objective characteristics of the particle in the particle swarm optimization algorithm, the fitness value representing a probability that the particle belongs to the objective. The disclosure also provides an objective identification method and driving assistance device. According to the disclosure, not only the identification rate can be increased but also application scenarios having different identification rate requirements can be satisfied.

A method, system, and computer program product, including generating a contrastive explanation for a decision of a classifier trained on structured data, highlighting an important feature that justifies the decision, and determining a minimal set of new values for features that alter the decision.

A machine learning system may automatically produce classifier algorithms and configuration parameters by selecting them into a set of predetermined unitary algorithms and associated parametrization values. Multiple digital representations of input object items may be produced by varying the position and orientation of the object to be classified and/or of the sensor to capture a digital representation of the object, and/or by varying a physical environment parameter which changes the digital representation capture of the object by the sensor. A robot arm or a conveyor may vary the object and/or the sensor positions and orientations. The machine learning system may employ genetic programming to facilitate the production of classifiers suitable for the classification of multiple digital representations of input object items. The machine learning system may automatically generate reference template signals as configuration parameters for the unitary algorithms to facilitate the production of classifiers suitable for the classification of multiple digital representations of input object items.