English  |  正體中文  |  简体中文  |  Items with full text/Total items : 66984/66984 (100%)
Visitors : 22955009      Online Users : 204
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version

    Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/79638

    Title: SVM(支持向量機)與Softmax在蝴蝶辨識問題中之觀察比較;The Comparison of Support Vector Machine and Softmax Classifier in Butterflies Recognition Problem
    Authors: 陳冠廷;Chen, Kuan-Ting
    Contributors: 數學系
    Keywords: 支持向量機;邏輯斯回歸;機器學習;影像辨識;SVM;Support Vector Machine;Logistic Regression;Softmax;Machine Learning;Image Identity
    Date: 2018-11-16
    Issue Date: 2019-04-02 15:09:39 (UTC+8)
    Publisher: 國立中央大學
    Abstract: 本文旨在探討 機器學習分類方法 ”支持向量機 ”及”Softmax ”在圖像辨識 上的訓練結果比較,也研讀當今常用優化算法熟知損失函數對參更新影響關係,兩個模型訓練將以蝴蝶圖片進行實作。
    經由線上開放的圖片庫網站,取得 8214 張共五類蝴蝶,並自製成數據樣 本集,分別帶入兩個 訓練 模型,觀察兩者訓練時間及準確率在迭代結果 上分析 比較 。而後再進一步 探討影響訓練結果的原因 ,在數據預處理 上,看 不同的數據庫量是否影響 訓練或驗證準確度。最後將模型結果對測試集 進行預測,觀察準確率分析探討影響結果的因素。;The purpose of this thesis is to explore the training resul ts of two deep learning models :(1) Support Vector Machine ;(2) Softmax Classifier in image recognition, and study the influence of loss functions on the iterative parameters . We demonstrate the results of these two models by use of the image s of butterflies.
    There are five types of butterflies with 8214 pictures obtained through the onlin e database website. We use these pictures for the files of data samples to two deep learning models, and observe the training time and accuracy. Next, we analyze the fitting situation to the itera tive results. Finally, we give the reason s why the performan ce of these two models are not ideal. Therefore, we are able to improve the performance by fixing the datasets .
    Appears in Collections:[數學研究所] 博碩士論文

    Files in This Item:

    File Description SizeFormat

    All items in NCUIR are protected by copyright, with all rights reserved.

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback  - 隱私權政策聲明