Abstract: An image sensor may be configured to output digital values for each pixel of the image sensor, where the digital values indicate a light intensity. Such digital values may range from 0 to 2n?1, where n represents the number of bits used to represent each value. To indicate which pixels of the image sensor are defective pixels, the image sensor may encode the pixel data such that one or more digital values indicate a defective pixel or type of defective pixels. The remaining digital values in the range represent the light intensity. An image signal processor may receive the encoded pixel data and determine which of the pixels are defective pixels directly from the encoded pixel data. The image signal processor may then perform a defective pixel correction process on the identified defective pixels.

Abstract: Examples described herein are relevant to robotic surgical systems, such as those used in spine surgery. Examples described herein include: a distal section of a robot arm, pods having fiducials, face switching angles, fiducial hollows, drape anchoring and sensing, selective face switching with active fiducials, pedal-less workflow, user interface control, hand guiding, robot egress, robot tool center point adjustment, collision reaction, dynamic screw placement ordering, flexible robot cart placement, depth gauges, implant checking, implant-to-instrument-checking, robot bed-side docking, workflow based cart immobilization, patient gross movement monitoring, selective brake control, auto vertical adjustment, gesture-based planning, automatic sleeve retention and retraction, among others.

Abstract: Systems and methods for processing surveillance video streams using image classification and object detection are described. Video data from a video image sensor may be processed using an image classifier to determine whether an object type is present in a video frame. If the object type is present, the video frame and/or subsequent video frames may be processed using an object detector to provide additional object data, such as position information, for use in other video surveillance processes. In some examples, an event message may be generated and sent to a video surveillance application in response to selective object detection.

Abstract: There is described herein a method of predicting disease progression risk in a subject with prostate cancer, the method comprising: a) providing a sample containing RNA and DNA material from tumour cells; b) determining or measuring values for substantially all of patient features listed for PRONTO-e or PRONTO-m in Table 6, and some or all reference or control features set forth in Table 6; c) comparing said patient features to the reference or control features; and d) computing a prediction score using a classifier that takes said patient feature values as input, the classifier having been previously trained on samples from a population of early prostate cancer patients.

Abstract: A device configured for more efficiently processing video images within a set of video image data to detect objects is described herein. The device may include a processor configured to execute a neural network such as a convolutional neural network. The device can receive video image data from a plurality of cameras, such as stationary cameras. The device can acquire a set of sample images from a stationary camera and submit them to a specialized neural network for processing to generate an attention mask. The attention mask can be generated from a variety of methods and is applied to each of the subsequently acquired images form the camera to narrow down areas where the convolutional neural network should process data. The application of attention masks to images within video image data creates masked images that can be processed to detect objects with much greater accuracy and fewer computational resources required.

Abstract: Embodiments herein describe circuitry with improved efficiency when executing layers in a nested neural network. As mentioned above, a nested neural network has at least one split operation where a tensor generated by a first layer is transmitted to, and processed by several branches in the neural network. Each of these branches can have several layers that have data dependencies which result in a multiply-add array sitting idly. In one embodiment, the circuitry can include a dedicated pre-pooler for performing a pre-pooling operation. Thus, the pre-pooling operation can be performing in parallel with other operations (e.g., the convolution performed by another layer). Once the multiply-add array is idle, the pre-pooling operation has already completed (or at least, has already started) which means the time the multiply-add array must wait before it can perform the next operation is reduced or eliminated.

Abstract: Systems and methods for processing surveillance video streams using image classification and object detection are described. Video data from a video image sensor may be processed using an image classifier to determine whether an object type is present in a video frame. If the object type is present, the video frame and/or subsequent video frames may be processed using an object detector to provide additional object data, such as position information, for use in other video surveillance processes. In some examples, an event message may be generated and sent to a video surveillance application in response to selective object detection.

Abstract: Systems and methods for surveillance video streams with embedded object data from another video camera are described. At least two video cameras are configured with fields of view to provide images of an object from alternative views. Video data for a primary video stream is received from one camera and secondary object data for the object from the other camera is embedded in the primary video stream. The primary video stream is sent to an analytics engine for processing the primary video and embedded secondary object data, such as performing facial recognition on a better image of a human face and/or feature vectors therefrom that are embedded in the primary video stream.

Abstract: A device configured for more efficiently processing video images within a set of video image data to detect objects is described herein. The device may include a processor configured to execute a neural network such as a convolutional neural network. The device can receive video image data from a plurality of cameras, such as stationary cameras. The device can acquire a set of sample images from a stationary camera and submit them to a specialized neural network for processing to generate an attention mask. The attention mask can be generated from a variety of methods and is applied to each of the subsequently acquired images form the camera to narrow down areas where the convolutional neural network should process data. The application of attention masks to images within video image data creates masked images that can be processed to detect objects with much greater accuracy and fewer computational resources required.

Abstract: Disclosed circuits and methods involve a first register configured to store of a first convolutional neural network (CNN) instruction during processing of the first CNN instruction and a second register configured to store a second CNN instruction during processing of the second CNN instruction. Each of a plurality of address generation circuits is configured to generate one or more addresses in response to an input CNN instruction. Control circuitry is configured to select one of the first CNN instruction or the second CNN instruction as input to the address generation circuits.

Abstract: A circuit arrangement includes an array of MAC circuits, wherein each MAC circuit includes a cache configured for storage of a plurality of kernels. The MAC circuits are configured to receive a first set of data elements of an IFM at a first rate. The MAC circuits are configured to perform first MAC operations on the first set of the data elements and a first one of the kernels associated with a first OFM depth index during a first MAC cycle, wherein a rate of MAC cycles is faster than the first rate. The MAC circuits are configured to perform second MAC operations on the first set of the data elements and a second one of the kernels associated with a second OFM depth index during a second MAC cycle that consecutively follows the first MAC cycle.

Abstract: Systems and methods for surveillance video streams with embedded object data from another video camera are described. At least two video cameras are configured with fields of view to provide images of an object from alternative views. Video data for a primary video stream is received from one camera and secondary object data for the object from the other camera is embedded in the primary video stream. The primary video stream is sent to an analytics engine for processing the primary video and embedded secondary object data, such as performing facial recognition on a better image of a human face and/or feature vectors therefrom that are embedded in the primary video stream.

Abstract: An integrated circuit (IC) includes a plurality of dies. The IC includes a plurality of memory channel interfaces configured to communicate with a memory, wherein the plurality of memory channel interfaces are disposed within a first die of the plurality of dies. The IC may include a compute array distributed across the plurality of dies and a plurality of remote buffers distributed across the plurality of dies. The plurality of remote buffers are coupled to the plurality of memory channels and to the compute array. The IC further includes a controller configured to determine that each of the plurality of remote buffers has data stored therein and, in response, broadcast a read enable signal to each of the plurality of remote buffers initiating data transfers from the plurality of remote buffers to the compute array across the plurality of dies.

Abstract: An integrated circuit (IC) includes a plurality of dies. The IC includes a plurality of memory channel interfaces configured to communicate with a memory, wherein the plurality of memory channel interfaces are disposed within a first die of the plurality of dies. The IC may include a compute array distributed across the plurality of dies and a plurality of remote buffers distributed across the plurality of dies. The plurality of remote buffers are coupled to the plurality of memory channels and to the compute array. The IC further includes a controller configured to determine that each of the plurality of remote buffers has data stored therein and, in response, broadcast a read enable signal to each of the plurality of remote buffers initiating data transfers from the plurality of remote buffers to the compute array across the plurality of dies.

Abstract: A system, according to one embodiment, includes: a plurality of tape reels; and a tape drive configured for reading data from tape stored on at least one of the plurality of tape reels. At least some of the tape reels have a tape wound thereon and a spring-like clip coupled to a free end of the tape. Moreover, the clip is selectively positionable in a wrapped position where the clip wraps around a portion of the tape when the tape is wound onto the reel, thereby holding the portion of the tape in place on the reel.

Abstract: The present invention relates to a water-soluble polymer complex that includes a water-soluble block copolymer and a magnetic nanoparticle, wherein the water-soluble polymer complex has a nonzero net magnetic moment in the absence of an applied magnetic field at ambient temperatures. The water-soluble block copolymer is preferably a diblock or triblock copolymer and the magnetic nanoparticle is preferably a ferrimagnetic or ferromagnetic nanoparticle. The water-soluble complexes may be derivatized with reactive groups and conjugated to biomolecules. Exemplary water-soluble polymer complexes covered under the scope of the invention include PEG112-b-PAA40 modified CoFe2O4; NH2-PEG112-b-PAA40 modified CoFe2O4; PNIPAM68-b-PAA28 modified CoFe2O4; and mPEG-b-PCL-b-PAA modified CoFe2O4.

Abstract: Systems, methods, and computer program embodiments are disclosed for adaptively displaying application performance data. In an embodiment, a plurality of performance monitoring data sources may be identified based on an application model that defines the topological structure of a software application. A request may be received for performance data associated with the application. One or more content options may then be determined based on the received request, and each content option may include one or more target performance metrics. Each content option may also be associated with one or more data sources. For each content option, the associated data sources may be queried to identify available data sources containing relevant performance data. A content option may be selected from the determined content options based on a priority associated with the content option. The performance data corresponding to the selected content option may subsequently be retrieved and presented for display.

Abstract: Described are embodiments to calibrate read sensors, which in turn may ensure that the equipment utilized to detect antigens is reliable and accurate. If it is determined that a read sensor is degraded a method of calibrating a read sensor of a read head may be used.

Abstract: A circuit arrangement includes an array of MAC circuits, wherein each MAC circuit includes a cache configured for storage of a plurality of kernels. The MAC circuits are configured to receive a first set of data elements of an IFM at a first rate. The MAC circuits are configured to perform first MAC operations on the first set of the data elements and a first one of the kernels associated with a first OFM depth index during a first MAC cycle, wherein a rate of MAC cycles is faster than the first rate. The MAC circuits are configured to perform second MAC operations on the first set of the data elements and a second one of the kernels associated with a second OFM depth index during a second MAC cycle that consecutively follows the first MAC cycle.

Abstract: An energy monitoring system includes a memory storing instructions to execute an energy modeling technique and processing circuitry for executing the instructions to operate the energy modeling technique. The energy modeling technique includes receiving energy data from a plurality of segments representative of one or more logical subgroups. The energy modeling technique includes categorizing the energy data of the logical subgroups into a plurality of segments. The energy modeling technique includes organizing the plurality of segments into a plurality of state-based hierarchical levels. The energy modeling technique includes calculating energy usage and factors associated with the plurality of state-based hierarchical levels via an energy model. The energy modeling technique includes outputting a visualization representative of the energy data corresponding to each of the segments to a monitoring and control system, resulting in a graphical representation accessible by a user-viewable screen.