Abstract: Aspects of the present disclosure provide a method for training a predictor that predicts performance of a plurality of machine learning (ML) models on platforms. For example, the method can include converting each of the ML models into a plurality of instructions or the instructions and a plurality of intermediate representations (IRs). The method can also include simulating execution of the instructions corresponding to each of the ML models on a platform and generating instruction performance reports. Each of the instruction performance reports can be associated with performance of the instructions corresponding to one of the ML models that are executed on the platform. The method can also include training the predictor with the instructions or the IRs as learning features and the instruction performance reports as learning labels, compiling the predictor into a library file, and storing the library file in a storage device.

Abstract: A system stores parameters of a feature extraction network and a refinement network. The system receives an input including a degraded image concatenated with a degradation estimation of the degraded image; performs operations of the feature extraction network to apply pre-trained weights to the input to generate feature maps; and performs operations of the refinement network including a sequence of dynamic blocks. One or more of the dynamic blocks dynamically generates per-grid kernels to be applied to corresponding grids of an intermediate image output from a prior dynamic block in the sequence. Each per-grid kernel is generated based on the intermediate image and the feature maps.

Abstract: According to a network space search method, an expanded search space is partitioned into multiple network spaces. Each network space includes a plurality of network architectures and is characterized by a first range of network depths and a second range of network widths. The performance of the network spaces is evaluated by sampling respective network architectures with respect to a multi-objective loss function. The evaluated performance is indicated as a probability associated with each network space. The method then identifies a subset of the network spaces that has the highest probabilities, and selects a target network space from the subset based on model complexity.

Abstract: A compensator compensates for the distortions of a power amplifier circuit. A power amplifier neural network (PAN) is trained to model the power amplifier circuit using pre-determined input and output signal pairs that characterize the power amplifier circuit. Then a compensator is trained to pre-distort a signal received by the PAN. The compensator uses a neural network trained to optimize a loss between a compensator input and a PAN output, and the loss is calculated according to a multi-objective loss function that includes one or more time-domain loss function and one or more frequency-domain loss functions. The trained compensator performs signal compensation to thereby output a pre-distorted signal to the power amplifier circuit.

Abstract: A neural network (NN) processing unit includes an operation circuit to perform tensor operations of a given layer of a neural network in one of a first number representation and a second number representation. The NN processing unit further includes a conversion circuit coupled to at least one of an input port and an output port of the operation circuit to convert between the first number representation and the second number representation. The first number representation is one of a fixed-point number representation and a floating-point number representation, and the second number representation is the other one of the fixed-point number representation and the floating-point number representation.

Abstract: An intelligent door lock, a control method thereof, and an unlocking apparatus and method thereof are provided. The unlocking method is adapted for an unlocking apparatus to unlock a door lock apparatus, and includes following steps. Receiving a plurality of broadcast packages sent by the door lock apparatus in response to an operation on the door lock apparatus, and detecting a variation in signal strengths of the broadcast packets caused by the operation. Reading a stage message, which is recorded in each of the broadcast packages, of the door lock apparatus corresponding to the operation. Determining whether a variation of the stage messages matches a variation of the signal strengths of the broadcast packages. Sending an unlocking signal to the door lock apparatus for executing unlocking if a determination result indicates match.

Abstract: An exemplary information sharing method is provided. The information sharing method includes a step of: broadcasting predetermined sharing information to a user terminal(s) within a preset region on a client side in response to a sharing request while an information sharing function is enable. An information sharing module, device and electronic apparatus using the same are also provided.

Abstract: A display system for improving visual comfort and a method of adaptively adjusting resolution of a display device are provided. The display system includes a display device, a memory, an image sensor, a face recognition unit, a distance detection unit, and a controller. The memory stores face representation data and user preference data. The image sensor captures an image and converts it into an electrical signal. The face recognition unit analyzes that electrical signal to recognize a face image and compares the recognized face image with the face representation data to generate a first signal. The distance detection unit analyzes the electrical signal to determine a distance between the display device and the user to generate a second signal. The controller then generates a parameter based on the first signal and the second signal and adjusts a display resolution of the display device based on the parameter.

Abstract: A driving support system with plural dimension processing units (DPUs) for indicating a condition of a surrounding area is disclosed. The driving support system of a vehicle includes plural image capturing devices disposed around the vehicle; at least a dimension processing unit (DPU) connected with the plural image capturing devices for receiving images from the plural image capturing devices and then producing plural related depth maps; a controller connected with the DPU for receiving the plural related depth maps and then producing an indicating data; and a display device connected with the controller for displaying the indicating data around the vehicle in a vertical view.

Abstract: A display system for improving visual comfort and a method of adaptively adjusting resolution of a display device are provided. The display system includes a display device, a memory, an image sensor, a face recognition unit, a distance detection unit, and a controller. The memory is configured to store face representation data and user preference data. The image sensor is positioned with respect to the display device for capturing an image and converting the image into an electrical signal. The face recognition unit is configured to analyze the electrical signal to recognize a face image of a user and comparing the recognized face image with the face representation data to generate a first signal. The distance detection unit is configured to analyze the electrical signal to determine a distance between the display device and the user to generate a second signal.

Abstract: A system and method of generating three-dimensional (3D) depth information is disclosed. The vanishing point of a two-dimensional (2D) input image is detected based on vanishing lines. The 2D image is classified and segmented into structures based on detected edges. The classified structures are then respectively assigned depth information.

Abstract: A driving support system with plural dimension processing units (DPUs) for indicating a condition of a surrounding area is disclosed. The driving support system of a vehicle includes plural image capturing devices disposed around the vehicle; at least a dimension processing unit (DPU) connected with the plural image capturing devices for receiving images from the plural image capturing devices and then producing plural related depth maps; a controller connected with the DPU for receiving the plural related depth maps and then producing an indicating data; and a display device connected with the controller for displaying the indicating data around the vehicle in a vertical view.