Optimization method and application method of deep learning neural network
A technology of deep neural network and deep learning, applied in the direction of neural learning methods, biological neural network models, neural architecture, etc., can solve the problems of large-scale deep neural network layers and difficult network analysis, so as to speed up the calculation speed and reduce equipment Spatial, maintaining the effect of classification performance strength
Pending Publication Date: 2022-01-14
NORTHWESTERN POLYTECHNICAL UNIV
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] Therefore, we need to continue to study the basis for the results given by the deep learning neural network model, and optimize the deep learning neural network model based on this basis to solve the problem that the network is difficult to analyze due to the large scale of deep neural network layers
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0050] The method of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments of the present invention.
[0051] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and examples.
[0052] It should be noted that the terminology used here is only for describing specific implementations, and is not intended to limit the exemplary implementations according to the present application. As used herein, unless the context clearly dictates otherwise, the singular is intended to include the plural, and it should also be understood that when the terms "comprise" and / or "comprise" are used in this specification, they mean There are features, steps, operations, means, components and / or combinations thereof.
...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an optimization method and an application method of a deep learning neural network. The method is simple in structure and reasonable in design, the influence degree of each layer of network in the to-be-analyzed deep neural network model on the whole network model is researched by quantifying the information increment of each convolutional layer of the deep neural network model, so that the deep neural network model is optimized, the size of the to-be-analyzed deep neural network model is reduced, therefore, the occupied equipment space is reduced, the operation calculation speed is increased, the equipment requirement required by model deployment is reduced, meanwhile, the original classification performance strength of the model can be maintained, and the use effect is good.
Description
technical field [0001] The invention belongs to the technical field of deep neural network interpretability, and in particular relates to an optimization method and an application method of a deep learning neural network. Background technique [0002] Deep learning refers to an operational architecture based on a set of algorithms that use deep maps with multiple processing layers to model high levels of abstraction in input data. Typically, deep learning architectures can include multiple layers of neurons and parameters. For example, as one of the deep learning architectures, convolutional neural network (CNN) is widely used in many artificial intelligence and machine learning applications, such as image classification, image captioning, visual question answering, and self-driving vehicles. [0003] Deep learning neural networks include a large number of parameters and require a lot of computation for image classification. Due to the increase in the size of training data...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/084G06N3/045Y02T10/40
Inventor 蒋雯肖陶黄凯耿杰邓鑫洋
Owner NORTHWESTERN POLYTECHNICAL UNIV