Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network system used to control an agent interacting with an environment to perform a specified task. One of the methods includes causing the agent to perform a task episode in which the agent attempts to perform the specified task; for each of one or more particular time steps in the sequence: generating a modified reward for the particular time step from (i) the actual reward at the time step and (ii) value predictions at one or more time steps that are more than a threshold number of time steps after the particular time step in the sequence; and training, through reinforcement learning, the neural network system using at least the modified rewards for the particular time steps.

A method for facial image recognition is provided. A plurality of original facial images are received. A plurality of standard facial images corresponding to the original facial images are generated through a standard face generation model. A recognition model is trained by using the original facial images and the standard facial images. The recognition model is tested by using the original facial image test set and a standard facial image test set until the recognition model recognizes that the first accuracy rate of the original facial image test set is higher than a first threshold value and the second accuracy rate of the standard facial image test set is higher than a second threshold value. The original facial image test set is composed of the original facial images obtained by sampling, and the standard facial image test set is composed of the standard facial images obtained by sampling.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for privacy preserving training of a machine learning model.

A distribution of a plurality of predictions generated by a deep neural network using sensor data is calculated, and the deep neural network includes a plurality of neurons. At least one of a measurement or a classification corresponding to an object is determined based on the distribution. The deep neural network generates each prediction of the plurality of predictions with a different number of neurons.

The present disclosure involves intelligent alignment of graphical elements for display within a graphical user interface. For instance, a graphics editing tool identifies position coordinates for a set of graphical elements and groups the position coordinates into one or more clusters. In some embodiments, the graphics editing tool selects the number of clusters for the clustering algorithm based on validity scores. For a given cluster, the graphics editing tool selects a centroid value of the cluster as an updated position value. The graphics editing tool aligns a subset of the graphical elements associated with the cluster by moving each graphical element to the updated position value. For instance, the graphic editing tool can change a horizontal coordinate value or a vertical component value for each graphical element to the centroid value. The graphics editing tool causes a display device to display the aligned graphical elements.

An image recognition method includes: selecting an augmentation process from augmentation processes based on a probability table, in response to an acquisition of an input image; acquiring an augmented image by augmenting the input image based on the selected augmentation process; and recognizing an object from the augmented image based on a recognition model.

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.

Embodiments discussed herein facilitate determination of one of a probability of prostate cancer recurrence-free survival or a risk factor associated with prostate cancer based on intra-tumor stromal morphology. Example embodiments can perform operations comprising: accessing a digitized histological image of a prostate of a patient, wherein the histological image comprises a region of interest associated with prostate cancer; identifying nuclei of intra-tumoral stromal cells within the region of interest; extracting, for the region of interest of the digitized histological image, one or more features describing the structure of the intra-tumoral stromal cells; and generating, via a model based at least on the one or more features, one of a probability of prostate cancer recurrence-free survival or a risk score associated with prostate cancer for the patient based at least on the extracted one or more features.

The invention is made out of methods for the development of Deep Neural Networks for cell detection and quantification in Whole Slide Images (WSI): 1. Method to create generic cell detector that detects the centers and contours of all cells in a WSI. 2. Method to create algorithms to detect cells of specific categories and that can classify between various types of cells of different categories. 3. Method for efficient cell annotation with online learning. 4. Method for efficient cell annotation with active learning. 5. Method for efficient cell annotation with online learning and data balancing. 6. Method for auto annotation of cells 7. Cell Detection Studio: a method to create an AI based system that provides pathologists with a semi-automatic tool to create new algorithms aiming to find cells of specific categories in WSI digitally scanned from histological specimen

Provided is an examination apparatus including a target image acquiring section that acquires a target image obtained by capturing an examination target; a target image masking section that masks a portion of the target image; a masked region predicting section that predicts an image of a masked region that is masked in the target image; a reproduced image generating section that generates a reproduced image using a plurality of predicted images predicted respectively for the plurality of masked regions; and a difference detecting section that detects a difference between the target image and the reproduced image.