Abstract: A method of operating a depth-wise separable convolutional (DSC) network on a DSC accelerator includes determining a difference between a first throughput associated with a depth-wise convolution (DWC) engine of the DSC accelerator and a second throughput associated with a point-wise convolution (PWC) engine of the DSC accelerator. The method also includes selectively activating, for each layer of the DSC network, each first processing elements (PEs) in one or more of a first set of columns of first PEs associated with the DWC engine and/or each second PE in one or more of a second set of columns associated with the PWC engine based on the difference between the first throughput and the second throughput. The method further includes processing, for each layer of the DSC network, an input via the DSC accelerator based on selectively activating each first PE and/or each second PE.

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for performing federated learning. One example method generally includes sending model update data to a server, generating training metadata using a trained local machine learning model and local validation data, and sending the training metadata to the server. The trained local machine learning model generally incorporates the model update data and global model data defining a global machine learning model, and the training metadata generally includes data bout the trained local machine learning model used to determine when to discontinue federated learning operations for training the global machine learning model. Another example method generally includes sending a global model to a federated learning client device and receiving training metadata from the federated learning client device.

Abstract: A computer-implemented method includes receiving a first input. The first input is interpolated based on a first shift along a first dimension and a second shift along a second dimension. A first output is generated based on the interpolated first input. The first output corresponds to a vectorized bilinear shift of the first input for use in place of grid sampling algorithms.

Abstract: A motionless parallel head reads an optical disk having an active surface encoded with an arrayed multiplicity of one-dimensional holograms. Each 1-D hologram is a computer-encoded representation of, typically, one 128 pixel slice of an image. A group, typically 128, 1-D holograms are positionally distributed, and positionally shifted or staggered one to the next, radially along the disk's active surface so as to fit a complete radius. Typically 14,000 groups are circumferentially-displaced around a 51/4" Compact Disk (CD), forming a herringbone pattern. During readout the encoded CD is simultaneously illuminated along the entirety of one of its radius lines within which a group of holographic data blocks are fitted.