Abstract: Numerous examples for performing tuning of a page or a word of non-volatile memory cells in an analog neural memory are disclosed. In one example, an analog neural memory system comprises an array of non-volatile memory cells arranged into rows and columns, each non-volatile memory cell comprising a word line terminal, a bit line terminal, and an erase gate terminal; a plurality of word lines, each word line coupled to word line terminals of a row of non-volatile memory cells; a plurality of bit lines, each bit line coupled to bit line terminals of a column of non-volatile memory cells; and a plurality of erase gate enable transistors, each erase gate enable transistor coupled to erase gate terminals of a word of non-volatile memory cells.

Abstract: Systems and methods are provided for using an external controller with an AR device. The system establishes, by one or more processors of the AR device, a communication with an external client device. The system overlays, by the AR device, a first AR object on a real-world environment being viewed using the AR device. The system receives interaction data from the external client device representing one or more inputs received by the external client device and, in response, modifies the first AR object by the AR device.

Abstract: The present disclosure relates to orally available stabilized supplement-containing articles (e.g., softgels). The stabilized supplement may be a probiotic, and may contain a stabilizing component derived from chocolate. The present disclosure also relates to methods of making such stabilized articles.

Abstract: Systems and methods are provided for performing operations on an augmented reality (AR) device. The system accesses, by the AR device, movement data comprising inertial measurement data and camera data. The system determines three-dimensional (3D) movement of the AR device based on the movement data. The system presents, by the AR device, an AR object on a real-world environment being viewed using the AR device. The system, in response to determining the 3D movement of the AR device, modifies the AR object by the AR device.

Abstract: A method includes receiving an input video stream and providing, to a convolutional neural network (CNN), multiple image frames of the video stream including a target pair of consecutive frames, a frame immediately preceding the target pair, and a frame immediately following the target pair. The method includes generating, by the CNN, multiple interpolated image frames by performing 3D space-time convolution on the multiple image frames and outputting a video stream in which the interpolated image frames are inserted between the frames of the target pair. The convolution may include passing a 3D filter over the multiple image frames in common width and height dimensions, and in a depth dimension representing the number of frames. Generating the interpolated image frames may include generating image data for multiple color channels in respective convolutional layers. The CNN may be trained to predict non-linear movements that occur over multiple image frames.

Abstract: In one embodiment, a method includes accessing a first set of images of multiple images of a scene, wherein the first set of images show the scene during a time period. The method includes generating, by processing the first set of images using a first machine-learning model, one or more attributes representing observed actions performed in the scene during the time period. The method includes predicting, by processing the generated one or more attributes using a second machine-learning model, one or more actions that would happen in the scene after the time period.

Abstract: In one embodiment, a method includes receiving a request for information associated with a video, determining the information associated with the video by processing the video using a machine-learning model which is based on a convolutional neural network comprising a plurality of layers, wherein at least one of the plurality of layers comprises one or more building blocks, wherein at least one of the one or more building blocks comprises a first filter configured to perform a three-dimensional (3D) pointwise convolutional operation and a second filter configured to perform a three-dimensional (3D) groupwise convolutional operation, and outputting the information associated with the video in response to the request.

Abstract: In one embodiment, a method includes, by a computing device, receiving a plurality of inputs for a convolution layer of a convolutional neural network, the convolution layer having one or more input channels and one or more output channels, wherein the inputs are received via the input channels, generating, by convolving the inputs with one or more two-dimensional filters, a plurality of intermediate values, and generating, by convolving the intermediate values with one or more one-dimensional filters, a plurality of outputs, wherein the one-dimensional filters receive the intermediate values from the two-dimensional filters via intermediate channels. The method may provide the outputs to a subsequent layer of the convolutional neural network via the output channels. Each of the two dimensions of the two-dimensional filter may correspond to a spatial dimension, and the one dimension of the one-dimensional filter may correspond to a temporal dimension.

Abstract: In one embodiment, a method includes accessing a first set of images of multiple images of a scene, wherein the first set of images show the scene during a time period. The method includes generating, by processing the first set of images using a first machine-learning model, one or more attributes representing observed actions performed in the scene during the time period. The method includes predicting, by processing the generated one or more attributes using a second machine-learning model, one or more actions that would happen in the scene after the time period.

Abstract: The present disclosure relates to orally available stabilized supplement-containing articles (e.g., softgels). The stabilized supplement may be a probiotic, and may contain a stabilizing component derived from chocolate. The present disclosure also relates to methods of making such stabilized articles.

Abstract: Systems, methods, and non-transitory computer-readable media can acquire video content for which video feature descriptors are to be determined. The video content can be processed based at least in part on a convolutional neural network including a set of two-dimensional convolutional layers and a set of three-dimensional convolutional layers. One or more outputs can be generated from the convolutional neural network. A plurality of video feature descriptors for the video content can be determined based at least in part on the one or more outputs from the convolutional neural network.

Abstract: Systems, methods, and non-transitory computer-readable media can acquire video content for which video feature descriptors are to be determined. The video content can be processed based at least in part on a convolutional neural network including a set of two-dimensional convolutional layers and a set of three-dimensional convolutional layers. One or more outputs can be generated from the convolutional neural network. A plurality of video feature descriptors for the video content can be determined based at least in part on the one or more outputs from the convolutional neural network.

Abstract: Systems, methods, and non-transitory computer-readable media can acquire video content for which video feature descriptors are to be determined. The video content can be processed based at least in part on a convolutional neural network including a set of two-dimensional convolutional layers and a set of three-dimensional convolutional layers. One or more outputs can be generated from the convolutional neural network. A plurality of video feature descriptors for the video content can be determined based at least in part on the one or more outputs from the convolutional neural network.

Abstract: Systems, methods, and non-transitory computer-readable media can obtain a set of video frames at a first resolution. Process the set of video frames using a convolutional neural network to output one or more signals, the convolutional neural network including (i) a set of two-dimensional convolutional layers and (ii) a set of three-dimensional convolutional layers, wherein the processing causes the set of video frames to be reduced to a second resolution. Process the one or more signals using a set of three-dimensional de-convolutional layers of the convolutional neural network. Obtain one or more outputs corresponding to the set of video frames from the convolutional neural network.

Abstract: Systems, methods, and non-transitory computer-readable media can obtain a set of video frames at a first resolution. Process the set of video frames using a convolutional neural network to output one or more signals, the convolutional neural network including (i) a set of two-dimensional convolutional layers and (ii) a set of three-dimensional convolutional layers, wherein the processing causes the set of video frames to be reduced to a second resolution. Process the one or more signals using a set of three-dimensional de-convolutional layers of the convolutional neural network. Obtain one or more outputs corresponding to the set of video frames from the convolutional neural network.

Abstract: A high insertion force ejector is provided. The high insertion force ejector includes an ejector mounting base, a pressure bar-ejector tooth, a first cam, and a second cam. The pressure bar-ejector tooth is connected to the ejector mounting base. A lever handle is operatively connected to the pressure bar-ejector and the ejector mounting base. The first cam and the second cam are operatively connected to the pressure bar-ejector tooth and the lever handle.

Abstract: Systems, methods, and non-transitory computer-readable media can acquire video content for which video feature descriptors are to be determined. The video content can be processed based at least in part on a convolutional neural network including a set of two-dimensional convolutional layers and a set of three-dimensional convolutional layers. One or more outputs can be generated from the convolutional neural network. A plurality of video feature descriptors for the video content can be determined based at least in part on the one or more outputs from the convolutional neural network.

Abstract: An apparatus is provided that includes a planar heat conducting material that comprises a first heat sink conduction portion configured to conduct heat between a first integrated circuit and a first heat sink, a second heat sink conduction portion configured to conduct heat between a second integrated circuit and a second heat sink, and a thermal bridge portion configured to conduct heat between the first heat sink conduction portion and the second heat sink conduction portion, such that the thermal bridge portion allows for flexural compensation for a height difference between the first integrated circuit and the second integrated circuit.

Abstract: A faceplate of a line card is provided, and in one example embodiment, includes a top panel including a portion angled downward towards a front side of the faceplate, the angled portion having a plurality of holes, and a front panel disposed on the front side of the faceplate, attached to the angled portion of the top panel on its top side and having a beveled edge at its bottom side, the angled portion of the top panel and the beveled edge of the front panel facilitating an intake area for air flow between the line card and other parallel line cards assembled on a chassis. In specific embodiments, the plurality of holes are arranged in a honeycomb pattern with each hole comprising a Reuleaux hexagon having rounded corners.

Abstract: An apparatus includes a frame and one or more heat generating elements supported by the frame. A plurality of ports are located at the front portion of the frame, and are electrically coupled to the heat generating elements. A faceplate is coupled to the front portion of the frame and includes one or more port openings to allow access to the ports and a plurality of airflow openings. Each of the airflow openings has a bottom edge aligned with the front portion of the frame and a top edge aligned with the top portion of the frame. The top edges of the airflow openings are set back a predetermined distance from the front portion of the frame.