A method for determining hard example sensor data inputs for training a task neural network is described. The task neural network is configured to receive a sensor data input and to generate a respective output for the sensor data input to perform a machine learning task. The method includes: receiving one or more sensor data inputs depicting a same scene of an environment, wherein the one or more sensor data inputs are taken during a predetermined time period; generating a plurality of predictions about a characteristic of an object of the scene; determining a level of inconsistency between the plurality of predictions; determining that the level of inconsistency exceeds a threshold level; and in response to the determining that the level of inconsistency exceeds a threshold level, determining that the one or more sensor data inputs comprise a hard example sensor data input.

Techniques for implementing a performance-adaptive sampling strategy towards fast and accurate graph neural networks are provided. In one technique, a graph that comprises multiple nodes and edges connecting the nodes is stored. An embedding for each node is initialized, as well as a sampling policy for sampling neighbors of nodes. One or more machine learning techniques are used to train a graph neural network and learn embeddings for the nodes. Using the one or more machine learning techniques comprises, for each node: (1) selecting, based on the sampling policy, a set of neighbors of the node; (2) based on the graph neural network and embeddings for the node and the set of neighbors, computing a performance loss; and (3) based on a gradient of the performance loss, modifying the sampling policy.

Disclosed herein are an apparatus and method for classifying clothing attributes based on deep learning. The apparatus includes memory for storing at least one program and a processor for executing the program, wherein the program includes a first classification unit for outputting a first classification result for one or more attributes of clothing worn by a person included in an input image, a mask generation unit for outputting a mask tensor in which multiple mask layers respectively corresponding to principal part regions obtained by segmenting a body of the person included in the input image are stacked, a second classification unit for outputting a second classification result for the one or more attributes of the clothing by applying the mask tensor, and a final classification unit for determining and outputting a final classification result for the input image based on the first classification result and the second classification result.

A method and system for evaluating performance of operation resources using Artificial Intelligence (AI) is disclosed. In some embodiments, the method includes receiving, each of a plurality of performance parameters associated with a set of operation resources. The method further includes determining a set of features for each of the plurality of performance parameters. The method further includes creating one or more feature vectors corresponding to each of the plurality of performance parameters. The one or more feature vectors are created based on a first pre-trained machine learning model. The method further includes assessing the one or more feature vectors, based on the first pre-trained machine learning model and classifying the set of operation resources into one of a set of performance categories based on the assessing of the one or more feature vectors. The method further includes evaluating performance of at least one of the set of operation resources.

A method and system are provided which facilitate construction of an ensemble of neural network kernel classifiers. The system divides a training set into partitions. The system trains, based on the training set, a first neural network encoder to output a first set of features, and trains, based on each respective partition of the training set, a second neural network encoder to output a second set of features. The system generates, for each respective partition, based on the first and second set of features, kernel models which output a third set of features. The system classifies, by a classification model, the training set based on the third set of features. The generated kernel models for each respective partition and the classification model comprise the ensemble of neural network kernel classifiers. The system predicts a result for a testing data object based on the ensemble of neural network kernel classifiers.

Various embodiments are generally directed to techniques for prediction based machine learning (ML) models, such as to utilize a ML model to generate predictions based on the output of another ML model. Some embodiments are particularly directed to a secondary ML model that revises predictions generated by a primary ML model based on structured input data. In many embodiments, the secondary ML model may utilize predictions from the primary ML model to learn metadata regarding the structured input data. In many such embodiments, the metadata regarding the structured input data may be used to revise the predictions from the primary ML model. For example, the secondary ML model may utilize a structure of the input data combined with patterns in the predictions from the primary ML model to revise the predictions from the primary ML model.

A method and apparatus for waking up a device, an electronic device, and a storage medium are provided, which are related to fields of image processing and deep learning. The method includes: acquiring an environment image of a surrounding environment of a target device in real time, and recognizing a face region of a user in the environment image; acquiring a plurality of facial landmarks in the face region, and acquiring a left eye image and a right eye image according to the facial landmarks; acquiring a left eye sight classification result and a right eye sight classification result according to the left eye image and the right eye image; and waking up the target device in a case of determining that the user is looking at the target device according to the left eye sight classification result and the right eye sight classification result.

An approach for improving determining a significant slice associated with a tumor from a volume of medical images is disclosed. The approach is based on the annotation of tumor range and the slice index in which the tumor appears to have the largest area. The approach infer a tumor growth classifier on sliding window of the volume slices and creates a discrete integral function out of the classifier predictions. The approach applies post processing on the discrete integral function which can include a smoothing function and a bias correction. The approach selects the slice index of maximum value from the post processing step.

Systems and methods of the present invention provide for: receiving a digital image data; modifying the digital image data to reduce a width of a feature within the digital image data; executing a dimension reduction process on the feature; storing a feature vector comprising: at least one feature for each of the received digital image data, and a correct or incorrect label associated with each feature vector; selecting the feature vector from a data store; training a classification software engine to classify each feature vector according to the label; classifying the image data as correct or incorrect according to a classification software engine; and generating an output labeling a second digital image data as correct or incorrect.

A system for performing adaptive focusing of a microscopy device comprises a microscopy device configured to acquire microscopy images depicting cells and one or more processors executing instructions for performing a method that includes extracting pixels from the microscopy images. Each set of pixels corresponds to an independent cell. The method further includes using a trained classifier to assign one of a plurality of image quality labels to each set of pixels indicating the degree to which the independent cell is in focus. If the image quality labels corresponding to the sets of pixels indicate that the cells are out of focus, a focal length adjustment for adjusting focus of the microscopy device is determined using a trained machine learning model. Then, executable instructions are sent to the microscopy device to perform the focal length adjustment.