Neural network model training method, device and system
A neural network model and neural network technology, applied in biological neural network models, neural learning methods, etc., can solve problems such as limited storage and computing resources, difficulty in improving convolutional neural network models, etc., and achieve the effect of increasing the number and improving performance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0021] According to an embodiment of the present invention, an embodiment of a training method for obtaining a neural network model is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings may be implemented in a computer system such as a set of computer-executable instructions. and, although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that herein.
[0022] The method embodiment provided in Embodiment 1 of the present application may be executed in a mobile terminal, a computer terminal, or a similar computing device. figure 1 A block diagram of the hardware structure of a computer terminal (or mobile device) for implementing a training method for acquiring a neural network model is shown. like figure 1 As shown, the computer terminal 10 (or mobile device 10 ) may include one or more processors 102 (shown as 102a, 102b, . or a processing devic...
Embodiment 2
[0103] According to an embodiment of the present invention, there is also provided a training device for a neural network model for implementing the above training method for acquiring a neural network model, image 3 is a schematic diagram of a training device for a neural network model according to Embodiment 2 of the present application, such as image 3 As shown, the apparatus 300 includes:
[0104] The preprocessing module 302 is configured to preprocess the initial data according to different types of preprocessing models to generate multiple groups of training data, wherein the training data includes elements and labels corresponding to the elements, and each group of training data corresponds to a different probability distribution.
[0105] The expansion module 304 is configured to expand the multiple sets of training data to the neighborhood to obtain a linear neighborhood element corresponding to each element in each set of training data.
[0106] The determining m...
Embodiment 3
[0118] Embodiments of the present invention also provide a training system for a neural network model, including:
[0119] processor; and
[0120] a memory, connected to the processor, for providing instructions for the processor to perform the following processing steps:
[0121] The initial data is preprocessed according to different types of preprocessing models, and multiple sets of training data are generated, wherein the training data includes: elements and labels corresponding to the elements, and each set of training data corresponds to a different probability distribution;
[0122] Extend multiple sets of training data to the neighborhood to obtain linear neighborhood elements corresponding to each element in each set of training data;
[0123] Input the linear neighborhood elements into the neural network, and determine the loss function according to the output result of the neural network, wherein the loss function is used to characterize the degree of deviation be...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More