DC 欄位 |
值 |
語言 |
DC.contributor | 資訊管理學系 | zh_TW |
DC.creator | 曾欽緹 | zh_TW |
DC.creator | ChinTi Tseng | en_US |
dc.date.accessioned | 2020-7-16T07:39:07Z | |
dc.date.available | 2020-7-16T07:39:07Z | |
dc.date.issued | 2020 | |
dc.identifier.uri | http://ir.lib.ncu.edu.tw:444/thesis/view_etd.asp?URN=107423036 | |
dc.contributor.department | 資訊管理學系 | zh_TW |
DC.description | 國立中央大學 | zh_TW |
DC.description | National Central University | en_US |
dc.description.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。 | zh_TW |
dc.description.abstract | 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. | en_US |
DC.subject | 機器學習 | zh_TW |
DC.subject | 深度學習 | zh_TW |
DC.subject | 神經架構搜尋 | zh_TW |
DC.subject | 基因演算法 | zh_TW |
DC.subject | 機器學習自動化 | zh_TW |
DC.subject | Machine Learning | en_US |
DC.subject | Evolutionary Algorithm | en_US |
DC.subject | Neural Architecture Search | en_US |
DC.subject | Automated Machine Learning | en_US |
DC.subject | Deep Learning | en_US |
DC.title | 以漸進式基因演算法實現神經網路架構搜尋最佳化 | zh_TW |
dc.language.iso | zh-TW | zh-TW |
DC.title | A Progressive Genetic-based Optimization for Network Architecture Search | en_US |
DC.type | 博碩士論文 | zh_TW |
DC.type | thesis | en_US |
DC.publisher | National Central University | en_US |