Neural network structure model search method, device and storage medium
A network model and network structure technology, applied in the field of deep learning, can solve problems such as increasing the complexity of neural networks, and achieve the effect of avoiding degradation
Active Publication Date: 2022-05-06
BEIJING XIAOMI INTELLIGENT TECH CO LTD
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] The deep learning neural network achieves end-to-end feature extraction, which is a huge improvement compared to manual feature extraction. At the same time, the artificially designed neural network architecture increases the complexity of the neural network.
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
[0052]Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present disclosure as recited in the appended claims.
[0053] The neural network structure model search method provided by the embodiment of the present disclosure can be applied to figure 1 The neural network architecture shown in the model search scenario. figure 1 It is a schematic diagram showing a search process of a neural network structure model according to some exemplary embodiments. refer to figure 1 As shown, the search proces...
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 disclosure relates to a neural network structure model search method, device and storage medium. Generate the initial generation network model structure population based on multi-objective optimization hyperparameters; select and crossover the current generation network model structure population; generate part of the network model structure based on reinforcement learning mutation, and randomly mutate the selected and crossover network model structure The rest of the network model structure; based on the network model structure generated by reinforcement learning mutation and the network model structure generated by random mutation, a new population of network model structure is generated; based on the current generation network model structure population and network model structure new population, the next generation network model is searched Structural population: use the next-generation network model structural population as the current generation network model structural population, repeat the above process until the multi-objective optimization state is optimal, and select neural network structural models suitable for different scenarios from the final generation network model structural population .
Description
technical field [0001] The present disclosure relates to the technical field of deep learning, and in particular to a neural network structure model search method, device and storage medium. Background technique [0002] The deep learning neural network achieves end-to-end feature extraction, which is a huge improvement compared to manual feature extraction. At the same time, the artificially designed neural network architecture increases the complexity of the neural network. [0003] With the development of technology, neural network architecture search (Neural Architecture Search, NAS) realizes the use of neural network to design neural network, which represents the future direction of machine learning. In NAS technology, an evolutionary algorithm or a reinforcement learning algorithm is used as a search strategy to search for a neural network structure model. Contents of the invention [0004] In order to overcome the problems existing in related technologies, the pres...
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 Patents(China)
IPC IPC(8): G06N3/08
CPCG06N3/086G06N3/084G06N3/092G06N3/082G06N3/045G06N3/0985G06F16/2468G06N3/02G06N5/04G06F7/58G06F18/217G06N3/047
Inventor 初祥祥许瑞军张勃李吉祥李庆源
Owner BEIJING XIAOMI INTELLIGENT TECH CO LTD