A Dimensionality Reduction Layer by Projection in a Convolutional Neural Network
碩士 === 國立臺灣大學 === 應用數學科學研究所 === 107 === In this research, we proposed a dimensionality reduction method that takes the place of the pooling methods. A pooling layer is usually put after a convolutional layer to summarize the output images from the convolutional layer. At the moment, the max-pooling...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2019
|
Online Access: | http://ndltd.ncl.edu.tw/handle/64absc |