Abstract: A method of performing automatic tuning on a deep learning model includes: utilizing an instruction-based learned cost model to estimate a first type of operational performance metrics based on a tuned configuration of layer fusion and tensor tiling; utilizing statistical data gathered during a compilation process of the deep learning model to determine a second type of operational performance metrics based on the tuned configuration of layer fusion and tensor tiling; performing an auto-tuning process to obtain a plurality of optimal configurations based on the first type of operational performance metrics and the second type of operational performance metrics; and configure the deep learning model according to one of the plurality of optimal configurations.

Abstract: A calibration apparatus includes a processor, an alignment device, and an arm. The alignment device captures images in a three-dimensional space, and a tool is arranged on a flange of the arm. The processor records a first matrix of transformation between an end-effector coordinate-system and a robot coordinate-system, and performs a tool calibration procedure according to the images captured by the alignment device for obtaining a second matrix of transformation between a tool coordinate-system and the end-effector coordinate-system. The processor calculates relative position of a tool center point of the tool in the robot coordinate-system based on the first and second matrixes, and controls the TCP to move in the three-dimensional space for performing a positioning procedure so as to regard points in an alignment device coordinate-system as points of the TCP, and calculates the relative positions of points in the alignment device coordinate-system and in the robot coordinate-system.

Abstract: Disclosed are methods and devices of generating predicted brain images. The present disclosure provides a method of generating a predicted brain image. The method comprises: receiving a first brain image; encoding the first brain image to generate a latent vector; and decoding the latent vector and one or more conditional features to generate the predicted brain image. The first brain image is generated by a magnetic resonance imaging (MRI) method. The one or more conditional features include at least one of: an age in future, a gender, previous brain images, omics features, and medical history. The latent vector is multiplied by a first normal distribution.

Abstract: A bicycle wheel assembly includes a hub disposed coaxially in a metal rim. A spoke unit interconnects the hub and the metal rim. The metal rim defines a tire-retention groove to receive a foam tire therein. The foam tire has an inner section disposed in the groove of the metal rim, and an outer section that projects outwardly from the groove. A tire reinforcing unit is embedded within the foam tire, and includes a non-stretchable strap embedded in the inner section of the foam tire and disposed around the metal rim, and a plurality of angularly spaced apart rigid strings which extend radially from the non-stretchable strap into the outer section of the foam tire.