.:: 回首頁 | 陽明交通大學 | 意見回饋 | 網站地圖 | 手機板 | English  ::.
國立陽明交通大學 回陽明交通大學 回本系應數首頁
最新消息 系所介紹 師資人員 學術研究 招生入學 修業規章 學生專區 系友會 FAQ

  • 招生與徵聘
  • 系所公告
  • 獎勵與補助
  • 工讀與就業
  • 學生活動
  • 其他消息

  • 演講公告月份查詢
  • 論文研討
  • 演講
  • 研討會

    • 微積分教學小組
    • 相關學術網站
    • 校內相關單位
    • 陽明交通大學
    • 意見回饋

演講公告

新聞標題: ( 2020-06-09 )

  • 演講主題:Un-rectifying Non-linear networks

  • 主講人:黃文良研究員(中央研究院資訊科學研究所)

  • 演講日期:2020年6月16日(星期二) 14:00 –15:00

  • 演講地點:(光復校區) 科學一館223室

  • 茶會時間:當天下午13:30 (科學一館205室)

  • 摘要內容:

    Abstract. I invent the novel "un-rectifying" technique for analysis of deep neural network (DNN).

    Deep feedforward neural networks with piecewise linear activations can be viewed as piecewise affine functions, affine linear on polytopes partitioning the input space. We thus consider networks with rectified linear units and max-pooling operations from a signal representation perspective. In this view, such representations mark the significant transition from using a single linear representation to utilizing a large collection of affine linear representations tailored to particular regions of the signal space. However, the expression power of a network cannot be fully leveraged in signal processing without explicit expressions of the affine linear operators, their domains, ranges, and composition from the weight and bias parameters of the network. This article addresses the problem and provides a precise description of the individual affine representations and corresponding domain regions that the neural network associates to each signal of the input space. In particular, we describe weighted atomic decompositions of the representations and, based on estimating their Lipschitz regularity, draw a connection between sparse or compressible weight distributions and the stability in representation and learning, independent of the network depth. Such analysis may facilitate understanding networks and promote further theoretical insight from both the signal processing and machine learning communities.

  • 相關檔案:talk_1090616.pdf


返回go back





  •         
  •         
  •         
  •         
  •         
  •         
  •         
  •         
  •         
  •    
  • English Version|
  • 意見回饋|
  • Go Top
  •         
  •         
  •         
  •         
  •         
  •         
  •         
  •         
  •         

本網站著作權屬於國立陽明交通大學 應用數學系  © 2023

地址: 300 新竹市大學路1001號 科學一館2樓

系辦電話 (03)5722088 傳真 (03) 5724679 電子郵件:lcchang@math.nctu.edu.tw

本系網站資訊開放宣告

本系個人資料保護暨資訊安全宣言

最後更新:2018-03-1 05:31:24 PM (CST)