Abstract: A key module includes a base plate, a circuit layer and a lifting mechanism. The circuit layer is disposed on the base plate. The lifting mechanism is pivotally connected with the base plate relative to the circuit layer, and the lifting mechanism has an abutment element. The abutment element could interfere with the circuit layer to reduce the noise generated by the key module during operation.

Abstract: The invention provides a portable CNC machine, including a body and four anchorage bases. The body is put on a surface of a work frame. The body is provided with a machining tool, a processing module and four take-up and pay-off modules, each take-up and pay-off module takes up and pays off a cable, a tail end of each cable is provided with an anchor, and the processing module is connected to and controls the four take-up and pay-off modules. The four anchorage bases are disposed at four corners of the work frame respectively, and stretch and hang the four anchors thereon respectively. The processing module controls the four take-up and pay-off modules to take up and pay off the cables to control the body to freely move on the work frame, and at the same time, the processing module controls the machining tool to carry out a machining operation.

Abstract: A method for enhancing kernel reparameterization of a non-linear machine learning model includes providing a predefined machine learning model, expanding a kernel of the predefined machine learning model with a non-linear network for convolution operation of the predefined machine learning model to generate the non-linear machine learning model, training the non-linear machine learning model, reparameterizing the non-linear network back to a kernel for convolution operation of the non-linear machine learning model to generate a reparameterized machine learning model, and deploying the reparameterized machine learning model to an edge device.

Abstract: A reparameterization method for initializing a machine learning model includes initializing a prefix layer of a first low dimensional layer in the machine learning model and a postfix layer of the first low dimensional layer, inverting the prefix layer to generate an inverse prefix layer of the first low dimensional layer, inverting the postfix layer to generate an inverse postfix layer of the first low dimensional layer, combining the inverse prefix layer, the first low dimensional layer and the inverse postfix layer to form a high dimensional layer, generating parallel operation layers from the high dimensional layer, and assigning initial weights to the parallel operation layers.

Abstract: A method for removing branches from trained deep learning models is provided. The method includes steps (i)-(v). In step (i), a trained model is obtained. The trained model has a branch structure involving one or more original convolutional layers and a shortcut connection. In step (ii), the shortcut connection is removed from the branch structure. In step (iii), a reparameterization model is built by linearly expanding each of the original convolutional layers into a reparameterization block in the reparameterization model. In step (iv), parameters of the reparameterization blocks are optimized by training the reparameterization model. In step (v), each of the optimized reparameterization blocks is transformed into a reparameterized convolutional layer to form a branchless structure that replaces the branch structure in the trained model.

Abstract: In aspects of the disclosure, a method, a system, and a computer-readable medium are provided. The method of building a kernel reparameterization for replacing a convolution-wise operation kernel in training of a neural network comprises selecting one or more blocks from tensor blocks and operations; and connecting the selected one or more blocks with the selected operations to build the kernel reparameterization. The kernel reparameterization has a dimension same as that of the convolution-wise operation kernel.

Abstract: A key module includes a base plate, a circuit layer and a lifting mechanism. The circuit layer is disposed on the base plate. The lifting mechanism is pivotally connected with the base plate relative to the circuit layer, and the lifting mechanism has an abutment element. The abutment element could interfere with the circuit layer to reduce the noise generated by the key module during operation.

Abstract: A key module includes a base plate, a circuit layer and a lifting mechanism. The circuit layer is disposed on the base plate. The lifting mechanism is pivotally connected with the base plate relative to the circuit layer, and the lifting mechanism has an abutment element. The abutment element could interfere with the circuit layer to reduce the noise generated by the key module during operation.

Abstract: A key module includes a base plate, a circuit layer and a lifting mechanism. The circuit layer is disposed on the base plate. The lifting mechanism is pivotally connected with the base plate relative to the circuit layer, and the lifting mechanism has an abutment element. The abutment element could interfere with the circuit layer to reduce the noise generated by the key module during operation.

Abstract: A key assembly including a base plate, a keycap, an elastic member, and a link member is provided. The base plate includes a body and a hook portion, the hook portion including a hole. The keycap is disposed on the base plate. The elastic member is disposed between the base plate and the keycap. The link member includes a connecting portion, a rod portion, and an end portion, the rod portion being assembled to the keycap, the connecting portion being connected between the rod portion and the end portion, and the end portion penetrating the hole, wherein an included angle between the end portion and the connecting portion is an obtuse angle.