以漸進式基因演算法實現神經網路架構搜尋最佳化;A Progressive Genetic-based Optimization for Network Architecture Search

NCUIR > School of Management at National Central University > Graduate Institute of Information Management > Electronic Thesis & Dissertation > Item 987654321/84016

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/84016

Title:	以漸進式基因演算法實現神經網路架構搜尋最佳化;A Progressive Genetic-based Optimization for Network Architecture Search
Authors:	曾欽緹;Tseng, ChinTi
Contributors:	資訊管理學系
Keywords:	機器學習;深度學習;神經架構搜尋;基因演算法;機器學習自動化;Machine Learning;Evolutionary Algorithm;Neural Architecture Search;Automated Machine Learning;Deep Learning
Date:	2020-07-16
Issue Date:	2020-09-02 17:55:29 (UTC+8)
Publisher:	國立中央大學
Abstract:	機器學習是一門從數據中由電腦自行學習得出特徵，再利用特徵對未知數據進行預測的技術。機器學習這門技術會因所針對的目標資料集不同，而設計出對應的模型架構，也因此所需對應專業知識、所需花費的研究時間與資源甚多，在普遍應用的期望下有一定的門檻與瓶頸。為了加速神經網路的建構，我們建構了一套基於演化演算法，結合深度學習技術，漸進式概念的建模演算法，搭配經過設計的細胞結構，應用在運算資源稀缺的環境下，並在針對特定資料集的背景下，自動搜尋出對應最優的神經網路架構。;No matter designing a new neural network (NN) architectures or modifying an existed model require both human expertise and intense computational resources. We propose a progressive strategy to develop models on a “meta” level which recently arose interests of experts. This meta-modeling algorithm is based on evolutionary algorithms and deep learning techniques to generate NN architectures for a given task automatically. The work we did also includes encoding a model structure into many “cells” in a continual representation. Therefore, after defining the cell structure and its topology, we find the structures for the given task cell by cell, brick by brick, and find a structure which has the highest accuracy eventually.
Appears in Collections:	[Graduate Institute of Information Management] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	108	View/Open

社群 sharing

Loading...