Abstract: Array of non-switchable non-scanning directional antennas combined to module with covering wide area of observation and simultaneous continuous illumination or receiving reflected signals from multiple targets, wherein antenna patterns are overlapping in as minimum one direction to form monopulse subarrays. Monopulse subarrays provides one iteration direction finding and references for automatic gain control and adaptation to transferring media. Each directional antenna coupled with separate transmitting/receiving means which providing continuous fast simultaneous multi-directional multi-band signals processing with high data rate. Non-scanning directional antennas do not need frequency dependent beamforming phase processor and provides continuous automatically controlled high gain in all channels independently and simultaneously.

Abstract: Passive radar system and method of detection of low-profile low altitude targets based on application of Low Earth Orbit (LEO) and Very Low Earth Orbit (VLEO) satellites signals. Staring array of directional antennas cover entire sky and provide continuous illumination (receiving reflected satellite signals) from multiple targets for fast detection, recognition and targets tracking and increasing detection range. Coupling of each directional antenna with separate receiver cannel allows fast continuous process of information from all targets simultaneously. Monopulse processing of signals from reference sub-set of antennas with overlap antenna patterns provides highest directing accuracy and better clutter/noise and media influence suppression. Directional antenna array does not need beam forming module. System has small weight, size, may be portable or mounted on light vehicle or small drone because small size and weight.

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: Machine learning is a process that learns a neural network model from a given dataset, where the model can then be used to make a prediction about new data. In order to reduce the size, computation, and latency of a neural network model, a compression technique can be employed which includes model sparsification. To avoid the negative consequences of pruning a fully pretrained neural network model and on the other hand of training a sparse model in the first place without any recovery option, the present disclosure provides a dynamic neural network model sparsification process which allows for recovery of previously pruned parts to improve the quality of the sparse neural network model.

Abstract: One embodiment of a method for training a first machine learning model having a different architecture than a second machine learning model includes receiving a first data set, performing one or more operations to generate a second data set based on the first data set and the second machine learning model, wherein the second data set includes at least one feature associated with one or more tasks that the second machine learning model was previously trained to perform, and performing one or more operations to train the first machine learning model based on the second data set and the second machine learning model.

Abstract: Various embodiments enable a robot, or other autonomous or semi-autonomous device or system, to receive data involving the performance of a task in the physical world. The data can be provided as input to a perception network to infer a set of percepts about the task, which can correspond to relationships between objects observed during the performance. The percepts can be provided as input to a plan generation network, which can infer a set of actions as part of a plan. Each action can correspond to one of the observed relationships. The plan can be reviewed and any corrections made, either manually or through another demonstration of the task. Once the plan is verified as correct, the plan (and any related data) can be provided as input to an execution network that can infer instructions to cause the robot, and/or another robot, to perform the task.

Abstract: Landmark detection refers to the detection of landmarks within an image or a video, and is used in many computer vision tasks such emotion recognition, face identity verification, hand tracking, gesture recognition, and eye gaze tracking. Current landmark detection methods rely on a cascaded computation through cascaded networks or an ensemble of multiple models, which starts with an initial guess of the landmarks and iteratively produces corrected landmarks which match the input more finely. However, the iterations required by current methods typically increase the training memory cost linearly, and do not have an obvious stopping criteria. Moreover, these methods tend to exhibit jitter in landmark detection results for video. The present disclosure improves current landmark detection methods by providing landmark detection using an iterative neural network.

Abstract: Systems and methods for more accurate and robust determination of subject characteristics from an image of the subject. One or more machine learning models receive as input an image of a subject, and output both facial landmarks and associated confidence values. Confidence values represent the degrees to which portions of the subject's face corresponding to those landmarks are occluded, i.e., the amount of uncertainty in the position of each landmark location. These landmark points and their associated confidence values, and/or associated information, may then be input to another set of one or more machine learning models which may output any facial analysis quantity or quantities, such as the subject's gaze direction, head pose, drowsiness state, cognitive load, or distraction state.

Abstract: Estimating motion of a human or other object in video is a common computer task with applications in robotics, sports, mixed reality, etc. However, motion estimation becomes difficult when the camera capturing the video is moving, because the observed object and camera motions are entangled. The present disclosure provides for joint estimation of the motion of a camera and the motion of articulated objects captured in video by the camera.

Abstract: Vision transformers are deep learning models that employ a self-attention mechanism to obtain feature representations for an input image. To date, the configuration of vision transformers has limited the self-attention computation to a local window of the input image, such that short-range dependencies are modeled in the output. The present disclosure provides a vision transformer that captures global context, and that is therefore able to model long-range dependencies in its output.

Abstract: The Bone Dust Trap for collecting bone dust during various surgical procedures for subsequent bone graft implantation. The device includes cylindrical housing unit covered with the lid, attached to the central pipe with the porous tip. The pipe connects the cyclone forming mechanism and filtrating membrane, located at the lower part of the central pipe. The membrane interlinks with the plurality of porous plates located along the walls of the cylinder. The cyclone forming mechanism, consisting of the inlet port with conical jet and the spiral helix, creates spiral movement of the incoming fluid. The liquid is further directed towards the 2-stage filtrating system with the said porous plates, where larger bone particles are accumulated, and then to the filtrating membrane, which collects smaller particles. The fluid is extracted through the central pipe. The lid can be removed to collect the bone particles from plates and membrane.

Abstract: A neural network is trained to identify one or more features of an image. The neural network is trained using a small number of original images, from which a plurality of additional images are derived. The additional images generated by rotating and decoding embeddings of the image in a latent space generated by an autoencoder. The images generated by the rotation and decoding exhibit changes to a feature that is in proportion to the amount of rotation.

Abstract: Multi-beam, multi-band, multi-function, non-scanning, non-switching system which can simultaneous be applied for communication, navigation, control, surveillance, data link. Antenna system with multiple overlap fixed beams provides simultaneous full/hemi-sphere covering without scanning or switching beams and provides higher data rates, reliability, and speed of communication. Automatic gain control and direction adjustment in each channel allows to use system in harsh urban or mountains conditions even on motion payload. Antenna system coupled with transmitters and receiver chains arranged as transceiver modules which can be distributed on ground, airborne, sea carrier/satellite or swarm of carriers or satellites and provides better protection against spoofing and EMP.

Abstract: Monopulse synthetic aperture radar for fast, high-resolution imaging of ground and/or airborne objects consists set of non-scanning transmitting and receiving antennas with overlap antenna patterns positioned in quadrature or multi-axis directions and covering wide space sector, wherein each of receiving antenna coupled to monopulse processor and separate receiver chain coupled with digital multi-channel processor. Application of monopulse and digital multi-axis multi-channel processing of all signals in receiving chains provides simultaneous fast signal processing from all space sector. Monopulse method in combine with multi-channel digital processing, where amplitudes, phase and frequency components shift of receiving signals processing relative to signals in overlap receiving antennas beams provides 3-5 times higher imaging resolution and allows to suppress influence of media and clutter. Array of directional antennas may be arranged for multi-frequency, multi-mode regimes.

Abstract: Systems and methods to detect one or more segments of one or more objects within one or more images based, at least in part, on a neural network trained in an unsupervised manner to infer the one or more segments. Systems and methods to help train one or more neural networks to detect one or more segments of one or more objects within one or more images in an unsupervised manner.

Abstract: A technique for managing a user interface in a continuous integration (CI) environment includes providing user-interface (UI) regions in a UI page downloaded from a server. The UI regions correspond to respective parameters of a CI job. In response to a change in a particular parameter associated with a UI region, the technique further includes updating, by the server, the UI page to contain code configured to hide a specified set of other UI regions, such as those rendered irrelevant based on the parameter change.

Abstract: One embodiment of the present invention sets forth a technique for executing a transformer neural network. The technique includes computing a first set of halting scores for a first set of tokens that has been input into a first layer of the transformer neural network. The technique also includes determining that a first halting score included in the first set of halting scores exceeds a threshold value. The technique further includes in response to the first halting score exceeding the threshold value, causing a first token that is included in the first set of tokens and is associated with the first halting score not to be processed by one or more layers within the transformer neural network that are subsequent to the first layer.

Abstract: A method, computer readable medium, and system are disclosed for visual sequence learning using neural networks. The method includes the steps of replacing a non-recurrent layer within a trained convolutional neural network model with a recurrent layer to produce a visual sequence learning neural network model and transforming feedforward weights for the non-recurrent layer into input-to-hidden weights of the recurrent layer to produce a transformed recurrent layer. The method also includes the steps of setting hidden-to-hidden weights of the recurrent layer to initial values and processing video image data by the visual sequence learning neural network model to generate classification or regression output data.

Abstract: Techniques for facilitating the composition of console commands for storage systems and appliances. The techniques include receiving a command prefix at a management console and accessing a plurality of first parameter designations associated with the command prefix from a first hierarchical level of a command tree. The techniques include receiving a selection of a first parameter designation from among the first parameter designations and accessing a plurality of second parameter designations associated with the first parameter designation from a second hierarchical level of the command tree. The techniques include receiving a selection of a second parameter designation from among the second parameter designations and merging the command prefix, the first parameter designation, and the second parameter designation to form a console command for performing a specified task or operation.

Abstract: Systems and methods for more accurate and robust determination of subject characteristics from an image of the subject. One or more machine learning models receive as input an image of a subject, and output both facial landmarks and associated confidence values. Confidence values represent the degrees to which portions of the subject's face corresponding to those landmarks are occluded, i.e., the amount of uncertainty in the position of each landmark location. These landmark points and their associated confidence values, and/or associated information, may then be input to another set of one or more machine learning models which may output any facial analysis quantity or quantities, such as the subject's gaze direction, head pose, drowsiness state, cognitive load, or distraction state.