Electronic equipment, neural network training device and computer readable medium
A technology of electronic equipment and neural network model, applied in the field of electronic equipment and computer readable medium, can solve the problems of long time period and slow training speed of neural network model, so as to reduce the time consumption, improve the training speed, and reduce the amount of data Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
no. 1 example
[0041] Figure 1A It is a schematic flow chart of the neural network model training method realized when the processor of the electronic device according to the first embodiment of the present application executes the program; the electronic device is used for the design of electromagnetic products, such as Figure 1A As shown, the neural network model training method includes:
[0042] Step S101, using the first training data of the electromagnetic product in the auxiliary domain to train the first neural network model, wherein the auxiliary domain is composed of at least the first training data and the first neural network model defined set;
[0043] In the embodiment of the present application, the auxiliary domain is a field (also referred to as a collection) that includes the training data of the first neural network model and the first neural network model; The first training data for training the neural network model, the first training data may be data of a rough model...
no. 2 example
[0089] Figure 2A It is a schematic flow chart of the neural network model training method realized when the processor of the electronic device according to the second embodiment of the present application executes the program; the electronic device is used for the design of electromagnetic products, such as Figure 2A As shown, the neural network model training method includes:
[0090] Step S201, using the first training data of the electromagnetic product in the auxiliary domain to train the first neural network model, wherein the auxiliary domain is composed of at least the first training data and the first neural network model defined set;
[0091] Figure 2B It is a schematic flowchart of step S201 in the neural network model training method realized when the processor of the electronic device according to the first embodiment of the present application executes the program; Figure 2B As shown, the processor executes the step of using the first training data of the e...
no. 3 example
[0116] Figure 3A It is a schematic structural diagram of a neural network model training device according to the third embodiment of the present application; the training device is used for the design of electromagnetic products, such as Figure 3A As shown, the device includes:
[0117]The first training unit 301 is configured to use the first training data of the electromagnetic product in an auxiliary domain to train the first neural network model, wherein the auxiliary domain consists of at least the first training data and the A set of definitions of the first neural network model; the parameter migration unit 302 is configured to extract the model parameters of the first neural network model, and migrate the model parameters of the first neural network model to the target domain based on a transfer learning mechanism , as a model parameter of the second neural network model in the target domain, wherein the structure of the second neural network model is the same as th...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More