Various embodiments include methods and devices for neural network pruning. Embodiments may include receiving as an input a weight tensor for a neural network, increasing a level of sparsity of the weight tensor generating a sparse weight tensor, updating the neural network using the sparse weight tensor generating an updated weight tensor, decreasing a level of sparsity of the updated weight tensor generating a dense weight tensor, increasing the level of sparsity of the dense weight tensor the dense weight tensor generating a final sparse weight tensor, and using the neural network with the final sparse weight tensor to generate inferences. Some embodiments may include increasing a level of sparsity of a first sparse weight tensor generating a second sparse weight tensor, updating the neural network using the second sparse weight tensor generating a second updated weight tensor, and decreasing the level of sparsity the second updated weight tensor.

This document describes “Multi-domain Neighborhood Embedding and Weighting” (MNEW) for use in processing point cloud data, including sparsely populated data obtained from a lidar, a camera, a radar, or combination thereof. MNEW is a process based on a dilation architecture that captures pointwise and global features of the point cloud data involving multi-scale local semantics adopted from a hierarchical encoder-decoder structure. Neighborhood information is embedded in both static geometric and dynamic feature domains. A geometric distance, feature similarity, and local sparsity can be computed and transformed into adaptive weighting factors that are reapplied to the point cloud data. This enables an automotive system to obtain outstanding performance with sparse and dense point cloud data. Processing point cloud data via the MNEW techniques promotes greater adoption of sensor-based autonomous driving and perception-based systems.

A system for assigning concepts to a medical image includes a visual feature module and a tagging module. The visual feature module is configured to obtain an image feature vector from the medical image. The tagging module is configured to apply a machine-learned algorithm to the image feature vector to assign a set of concepts to the image. The system may also include a text report generator that is configured to generate a written report describing the medical image based on the set of concepts assigned to the medical image.

System, methods, and other embodiments described herein relate to training a depth model for monocular depth estimation. In one embodiment, a method includes generating, as part of training the depth model according to a supervised training stage, a depth map from a first image of a pair of training images using the depth model. The pair of training images are separate frames depicting a scene from a monocular video. The method includes generating a transformation from the first image and a second image of the pair using a pose model. The method includes computing a supervised loss based, at least in part, on reprojecting the depth map and training depth data onto an image space of the second image according to at least the transformation. The method includes updating the depth model and the pose model according to at least the supervised loss.

A method of reconstructing magnetic resonance (MR) image data from k-space data. The method includes obtaining k-space data of an image region of a subject; and reconstructing, using a sparse image coding procedure, the MR image data from the k-space data by performing an iterative optimization method. The optimization method includes a data consistency iteration step and a denoising iteration step applied to MR image data generated by the data consistency iteration step. The denoising iteration step incorporates a sparsifying operation to provide a sparse representation of the MR image data for the imaged region as an input to the data consistency iteration step.

A system for predicting medications to prescribe to a patient includes a text encoding module and a medication prediction module. The text encoding module is configured to obtain a clinical-information vector from clinical information of the patient. The medication prediction module configured to apply a machine-learned medication-prediction algorithm to the clinical-information vector to select a subset of medications to prescribe to the patient. The machine-learned medication-prediction algorithm is designed with a diversity-promoting regularization model, and is configured to simultaneously consider correlations among different medications and dependencies between patient information and medications when selecting a subset of medications to prescribe to the patient.

A system for assigning concepts to a medical image includes a visual feature module and a tagging module. The visual feature module is configured to obtain an image feature vector from the medical image. The tagging module is configured to apply a machine-learned algorithm to the image feature vector to assign a set of concepts to the image. The system may also include a text report generator that is configured to generate a written report describing the medical image based on the set of concepts assigned to the medical image.

A computer-implemented method is disclosed for compressing a deep neural network (DNN) model by DNN weight pruning to accelerate DNN inference on mobile devices. The method includes the steps of (a) performing an intra-convolution kernel pruning of the DNN model wherein a fixed number of weights are pruned in each convolution kernel of the DNN model to generate sparse convolution patterns; (b) performing inter-convolution kernel pruning of the DNN model to generate connectivity sparsity, wherein inter-convolution kernel pruning comprises cutting connections between given input and output channels of the DNN model to remove corresponding kernels; and (c) training the DNN model compressed in steps (a) and (b).

An object recognition method and apparatus for a deformed image are provided. The method includes: inputting an image into a preset localization network to obtain a plurality of localization parameters for the image, wherein the preset localization network comprises a preset number of convolutional layers, and wherein the plurality of localization parameters are obtained by regressing image features in a feature map that is generated from a convolution operation on the image; performing a spatial transformation on the image based on the plurality of localization parameters to obtain a corrected image; and inputting the corrected image into a preset recognition network to obtain an object classification result for the image. In the process of the neural network based object recognition, the embodiment of the present application first transforms the deformed image that has deformation, and then performs the object recognition on the transformed image.

Various embodiments of systems and methods for cross media joint friend and item recommendations are disclosed herein.