According to one embodiment, a learning method for causing a second statistical model to learn using a first statistical model is provided. The method includes obtaining a first learning image, cutting out each local area of the obtained first learning image, and obtaining a first prediction value output from the first statistical model by inputting each local area to the first statistical model and obtaining a second prediction value output from the second statistical model by inputting the entire area of the first learning image to the second statistical model, and causing the second statistical model to learn based on a difference between the first prediction value and the second prediction value.

A computing system generates a training data set for training the prediction model to detect defects present in a target surface of a target specimen and training the prediction model to detect defects present in the target surface of the target specimen based on the training data set. The computing system generates the training data set by identifying a set of images for training the prediction model, the set of images comprising a first subset of images. A deep learning network generates a second subset of images for subsequent labelling based on the set of images comprising the first subset of images. The deep learning network generates a third subset of images for labelling based on the set of images comprising the first subset of images and the labeled second subset of images. The computing system continues the process until a threshold number of labeled images is generated.

A computing device trains a fair machine learning model. A prediction model is trained to predict a target value. For a number of iterations, a weight vector is computed using the bound value based on fairness constraints defined for a fairness measure type; a weight value is assigned to each observation vector based on the target value and a sensitive attribute value; the prediction model is trained with each weighted observation vector to predict the target value; and a conditional moments vector is computed based on the fairness constraints and the target and sensitive attribute values. Conditional moments difference values are computed. When the conditional moments difference values indicate to adjust the bound value, the bound value is updated and the process is repeated with the bound value replaced with the updated bound value until the conditional moments difference values indicate no further adjustment of the bound value is needed.

A system for determining a goodness of a deep learning model comprises a memory coupled with a processor. The processor accesses a first set of vectors representative of images of a biological assay. The vectors of the first set of vectors are outputs of a first deep learning model. The processor creates a first distribution of a first plurality of pairwise comparisons of vectors, of the first set of vectors, which were generated from image pairs with similar cell perturbations. The processor creates a second distribution of a second plurality of pairwise comparisons of vectors, of the first set of vectors, which were generated from image pairs with dissimilar cell perturbations. The processor determines a difference between the first distribution and the second distribution and uses the difference to make a determination of goodness of the deep learning model as applied to the biological assay.

A medical system may utilize a modular and extensible sensing device to derive a two-dimensional (2D) or three-dimensional (3D) human model for a patient in real-time based on images of the patient captured by a sensor such as a digital camera. The 2D or 3D human model may be visually presented on one or more devices of the medical system and used to facilitate a healthcare service provided to the patient. In examples, the 2D or 3D human model may be used to improve the speed, accuracy and consistency of patient positioning for a medical procedure. In examples, the 2D or 3D human model may be used to enable unified analysis of the patient's medical conditions by linking different scan images of the patient through the 2D or 3D human model. In examples, the 2D or 3D human model may be used to facilitate surgical navigation, patient monitoring, process automation, and/or the like.

Broadly speaking, embodiments of the present techniques provide methods for inspecting a neural network, such that a neural network can be made more transparent. The inspection is performed with respect to each decision or output made by the neural network. The method comprises outputting a dependency graph, for each inspection/decision. Each dependency graph shows which neurons are used to make each individual decision made by the neural network, and how those neurons interact with or relate to each other. Specifically, the dependency graph shows the dependencies between neurons in adjacent layers. By understanding which neurons are used to make individual decisions, and the dependencies between neurons, the neural network can be better understood, audited, optimised, and debugged, for example.

Human mesh model recovery may utilize prior knowledge of the hierarchical structural correlation between different parts of a human body. Such structural correlation may be between a root kinematic chain of the human body and a head or limb kinematic chain of the human body. Shape and/or pose parameters relating to the human mesh model may be determined by first determining the parameters associated with the root kinematic chain and then using those parameters to predict the parameters associated with the head or limb kinematic chain. Such a task can be accomplished using a system comprising one or more processors and one or more storage devices storing instructions that, when executed by the one or more processors, cause the one or more processors to implement one or more neural networks trained to perform functions related to the task.

Various embodiments of the teachings herein include a method for training and updating a backend-side classifier comprising: receiving, in a backend-device, from at least one vehicle, classification data along with a respective classification result generated by a vehicle-side classifier; and training the backend-side classifier using the classification data and, if available, a corrected respective classification result as annotation.

A learning model generation apparatus includes: a processor configured to obtain captured image data and plural setting values which are set for each imaging condition in a case where the image data is captured and have dependency relationships with one another; calculate an evaluation value for classifying image information which is information obtained from the image data by using the plural setting values; classify the image information based on the evaluation value; and generate a learning model for each classification by using the image information.

According to one embodiment, a learning apparatus includes processing circuitry. The processing circuitry acquires a plurality of learning samples to be learned and a plurality of target labels associated with the respective learning samples, iteratively learns a learning model so that a learning error between output data corresponding to the learning sample and the target label is small with respect to the learning model to which the output data is output by inputting the learning sample, and displays a layout image in which at least some of the learning samples are arranged based on a learning progress regarding the iterative learning of the learning model and a plurality of the learning errors.