Unlock instant, AI-driven research and patent intelligence for your innovation.

A Deconvolutional Neural Network Training Method

A neural network training and deconvolution technology, applied in the field of deconvolution neural network training, to achieve the effects of improving training convergence efficiency and convergence accuracy, improving classification accuracy, and reducing training costs

Active Publication Date: 2018-01-19
BEIJING UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it still needs more work and improvement to extend such methods to multi-layer deconvolutional neural network models.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Deconvolutional Neural Network Training Method
  • A Deconvolutional Neural Network Training Method
  • A Deconvolutional Neural Network Training Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Such as Figure 4 As shown, this deconvolutional neural network training method includes a training phase and a reconstruction phase, and the training phase includes the following steps:

[0024] (1) Preprocess the training image: select the training set image, process it as a grayscale image, and unify the length and width pixels;

[0025] (2) Batch setting is performed on the training images: according to the application of the trained network, the training images are divided into batches;

[0026] (3) Set the network training parameters of the training image. The network training parameters of the training image include the number of network layers, the filter size of each layer, the number of feature maps of each layer, the number of FISTA reconstruction steps and reconstruction steps, the total number of epoch cycles, Feature map sparse control parameters;

[0027] (4) Start the first layer training: initialize the first layer feature map and the first layer filt...

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

No PUM Login to View More

Abstract

The invention discloses a deconvolution neural network training method, which can effectively extract image features, is beneficial to the improvement of the classification accuracy rate, improves the training convergence efficiency and convergence accuracy of the deconvolution neural network, and reduces the deconvolution neural network. The training cost in practical applications can also be applied to solve other optimization problems based on convolution operations. This deconvolutional neural network training method includes a training phase and a reconstruction phase, and the training phase includes steps: (1) preprocessing the training images; (2) batch setting the training images; (3) setting the network of the training images Training parameters; (4) start the first layer of training; the reconstruction stage includes steps: (5) preprocessing the image to be reconstructed; (6) setting the network training parameters of the image to be reconstructed; (7) inputting the image to be reconstructed by batch images until the reconstruction of all batch images is completed.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to a deconvolution neural network training method. Background technique [0002] Deep learning is one of the research hotspots in the field of artificial intelligence. Based on the idea of ​​neural networks, deep learning is committed to imitating the hierarchical perception of the human brain. By constructing a multilayer perceptron (Multilayer Perception, MLP), an abstract high-level representation that can represent attribute categories or features is combined from low-level features, thus becoming One of the effective models for extracting complex image features at present. [0003] Classic deep learning models mainly include Deep Belief Networks (DBNs), multi-layer sparse auto-encoding models (Auto Encode, AE) and convolutional neural networks (Convolutional Neural Networks, CNNs). Usually, these models extract features from the input image through...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06N3/02
Inventor 施云惠张轶昀丁文鹏尹宝才
Owner BEIJING UNIV OF TECH