Abstract: The present invention relates to an immediate release tablet composition comprising axitinib form IV characterized by an XRPD pattern comprising the peaks at about 8.9, 12.0, 14.6, 15.2, 15.7, 17.8, 19.1, 20.6, 21.6, 23.2, 24.2, 24.9, 26.1 and 27.5±0.1 degrees 2?, when measured with Cu K?1 radiation and one or more pharmaceutically acceptable excipients, wherein the composition exhibits a dissolution rate between 40% and 70% in 30 minutes when tested in 900 ml 0.01 N hydrochloric acid pH 2.0 at 37° C., 75 rpm in a USP apparatus II.

Abstract: Approaches presented herein provide for semantic data matching, as may be useful for selecting data from a large unlabeled dataset to train a neural network. For an object detection use case, such a process can identify images within an unlabeled set even when an object of interest represents a relatively small portion of an image or there are many other objects in the image. A query image can be processed to extract image features or feature maps from only one or more regions of interest in that image, as may correspond to objects of interest. These features are compared with images in an unlabeled dataset, with similarity scores being calculated between the features of the region(s) of interest and individual images in the unlabeled set. One or more highest scored images can be selected as training images showing objects that are semantically similar to the object in the query image.

Abstract: One embodiment of the present invention sets forth a technique for training an image classifier. The technique includes training a first vision transformer model to generate patch labels for corresponding images patches of images, converting the patch labels to token labels, and training a second vision transformer model to classify images based on the token labels.

Abstract: Apparatuses, systems, and techniques are presented to determination about objects in an environment. In at least one embodiment, a neural network can be used to determine one or more positions of one or more objects within a three-dimensional (3D) environment and to generate a segmented map of the 3D environment based, at least in part, on one or more two dimensional (2D) images of the one or more objects.

Abstract: Apparatuses, systems, and techniques of using one or more machine learning processes (e.g., neural network(s)) to predict occupancy using an image input. In at least one embodiment, image data is processed using a neural network to predict occupancy in a 3D voxel space. In at least one embodiment, image data is processed using a neural network to detect objects in a 3D space.

Abstract: In various examples, systems and methods are disclosed relating to using neural networks for object detection or instance/semantic segmentation for, without limitation, autonomous or semi-autonomous systems and applications. In some implementations, one or more neural networks receive an image (or other sensor data representation) and a bounding shape corresponding to at least a portion of an object in the image. The bounding shape can include or be labeled with an identifier, class, and/or category of the object. The neural network can determine a mask for the object based at least on processing the image and the bounding shape. The mask can be used for various applications, such as annotating masks for vehicle or machine perception and navigation processes.

Abstract: In various examples, bi-directional projection techniques may be used to generate enhanced Bird's-Eye View (BEV) representations. For example, a system(s) may generate one or more BEV features associated with a BEV of an environment using a projection process that associates 2D image features to one or more first locations of a 3D space. At least partially using the BEV feature(s), the system(s) may determine one or more second locations of the 3D space that correspond to one or more regions of interest in the environment. The system(s) may then generate one or more additional BEV features corresponding to the second location(s) using a different projection process that associates the second location(s) from the 3D space to at least a portion of the 2D image features. The system(s) may then generate an updated BEV of the environment based at least on the BEV feature(s) and/or the additional BEV feature(s).

Abstract: In various examples, systems and methods are disclosed relating to synthetic data generation using viewpoint augmentation for autonomous and semi-autonomous systems and applications. One or more circuits can identify a set of sequential images corresponding to a first viewpoint and generate a first transformed image corresponding to a second viewpoint using a first image of the set of sequential images as input to a machine-learning model. The one or more circuits can update the machine-learning model based at least on a loss determined according to the first transformed image and a second image of the set of sequential images.

Abstract: In various examples, temporal-based perception for autonomous or semi-autonomous systems and applications is described. Systems and methods are disclosed that use a machine learning model (MLM) to intrinsically fuse feature maps associated with different sensors and different instances in time. To generate a feature map, image data generated using image sensors (e.g., cameras) located around a vehicle are processed using a MLM that is trained to generate the feature map. The MLM may then fuse the feature maps in order to generate a final feature map associated with a current instance in time. The feature maps associated with the previous instances in time may be preprocessed using one or more layers of the MLM, where the one or more layers are associated with performing temporal transformation before the fusion is performed. The MLM may then use the final feature map to generate one or more outputs.

Abstract: The invention relates to a test sensor and a heater and thermocouple device for use in a test sensor and other assays, such as a diagnostic test sensor or strip and to a method of manufacturing a test sensor and a device and a method of conducting an assay using the test sensor or device. The invention relates to a test sensor comprising a heater and thermocouple device (100), the heater and thermocouple device (100) comprising: a substrate (10); on the substrate (10), a first layer (12) of a first conductive material of a first conductivity comprising: a first thermocouple element (14); a first connector track (16) connected to the first thermocouple element (14); a resistive heater element (20); and in which at least part of the first thermocouple element (14) is comprised of a portion of the resistive heater element (20); a second layer (22) of a second conductive material of a second conductivity comprising: a second thermocouple element (24) in contact with the first thermocouple element (14) (e.g.

Abstract: A mounting bracket system for a vehicle roof, and a method for its attachment to a vehicle having a side rail including a drip well, is contemplated in which no drilling of holes or other permanent modifications to the vehicle roof is required, and in which each individual mounting bracket may be independently fixed in place without requiring any structural support from interconnections with any other mounting bracket via crossbars or other interconnections. In this regard, a number of problems associated with prior mounting bracket systems may be overcome.

Abstract: Apparatuses, systems, and techniques of using one or more machine learning processes (e.g., neural network(s)) to process data (e.g., using hierarchical self-attention). In at least one embodiment, image data is classified using hierarchical self-attention generated using carrier tokens that are associated with windowed subregions of the image data, and local attention generated using local tokens within the windowed subregions and the carrier tokens.

Abstract: Class agnostic object mask generation uses a vision transformer-based auto-labeling framework requiring only images and object bounding boxes to generate object (segmentation) masks. The generated object masks, images, and object labels may then be used to train instance segmentation models or other neural networks to localize and segment objects with pixel-level accuracy. The generated object masks may supplement or replace conventional human generated annotations. The human generated annotations may be misaligned compared with the object boundaries, resulting in poor quality labeled segmentation masks. In contrast with conventional techniques, the generated object masks are class agnostic and are automatically generated based only on a bounding box image region without relying on either labels or semantic information.

Abstract: Systems and methods are disclosed for improving natural robustness of sparse neural networks. Pruning a dense neural network may improve inference speed and reduces the memory footprint and energy consumption of the resulting sparse neural network while maintaining a desired level of accuracy. In real-world scenarios in which sparse neural networks deployed in autonomous vehicles perform tasks such as object detection and classification for acquired inputs (images), the neural networks need to be robust to new environments, weather conditions, camera effects, etc. Applying sharpness-aware minimization (SAM) optimization during training of the sparse neural network improves performance for out of distribution (OOD) images compared with using conventional stochastic gradient descent (SGD) optimization. SAM optimizes a neural network to find a flat minimum: a region that both has a small loss value, but that also lies within a region of low loss.

Abstract: A mounting bracket system for a vehicle roof, and a method for its attachment to a vehicle having a side rail including a drip well, is contemplated in which no drilling of holes or other permanent modifications to the vehicle roof is required, and in which each individual mounting bracket may be independently fixed in place without requiring any structural support from interconnections with any other mounting bracket via crossbars or other interconnections. In this regard, a number of problems associated with prior mounting bracket systems may be overcome.

Abstract: An artificial intelligence framework is described that incorporates a number of neural networks and a number of transformers for converting a two-dimensional image into three-dimensional semantic information. Neural networks convert one or more images into a set of image feature maps, depth information associated with the one or more images, and query proposals based on the depth information. A first transformer implements a cross-attention mechanism to process the set of image feature maps in accordance with the query proposals. The output of the first transformer is combined with a mask token to generate initial voxel features of the scene. A second transformer implements a self-attention mechanism to convert the initial voxel features into refined voxel features, which are up-sampled and processed by a lightweight neural network to generate the three-dimensional semantic information, which may be used by, e.g., an autonomous vehicle for various advanced driver assistance system (ADAS) functions.

Abstract: Approaches for training data set size estimation for machine learning model systems and applications are described. Examples include a machine learning model training system that estimates target data requirements for training a machine learning model, given an approximate relationship between training data set size and model performance using one or more validation score estimation functions. To derive a validation score estimation function, a regression data set is generated from training data, and subsets of the regression data set are used to train the machine learning model. A validation score is computed for the subsets and used to compute regression function parameters to curve fit the selected regression function to the training data set. The validation score estimation function is then solved for and provides an output of an estimate of the number additional training samples needed for the validation score estimation function to meet or exceed a target validation score.

Abstract: In various examples, estimating optimal training data set sizes for machine learning model systems and applications. Systems and methods are disclosed that estimate an amount of data to include in a training data set, where the training data set is then used to train one or more machine learning models to reach a target validation performance. To estimate the amount of training data, subsets of an initial training data set may be used to train the machine learning model(s) in order to determine estimates for the minimum amount of training data needed to train the machine learning model(s) to reach the target validation performance. The estimates may then be used to generate one or more functions, such as a cumulative density function and/or a probability density function, wherein the function(s) is then used to estimate the amount of training data needed to train the machine learning model(s).

Abstract: A torque converter includes a front cover, an impeller assembly, a turbine assembly, a lock-up clutch, a backing plate, and a flow plate. The front cover is arranged to receive a torque. The lock-up clutch includes a piston and a seal plate disposed axially between the piston and a turbine shell. The backing plate is non-rotatably connected to the seal plate and is sealed to the piston. The flow plate is disposed axially between the backing plate and the front cover. The flow plate is non-rotatably connected to the backing plate and the front cover. A through-bore extends axially through the backing plate and the flow plate. A first chamber is bounded at least in part by the piston, the seal plate, and the backing plate, and a second chamber is bounded at least in part by the front cover, the piston, the backing plate, and the flow plate.