教學大綱 Syllabus

科目名稱:卷積神經網路與視覺識別

Course Name: Convolutional Neural Networks and Visual Recognition

修別:選

Type of Credit: Elective

3.0

學分數

Credit(s)

30

預收人數

Number of Students

課程資料Course Details

課程簡介Course Description

The course objective is the introduction of Convolutional Neural Networks and the visual recognition with the infrastructure of Tensorflow and GPUs.

核心能力分析圖 Core Competence Analysis Chart

能力項目說明


    課程目標與學習成效Course Objectives & Learning Outcomes

    The course objective is the introduction of the Convolutional Neural Networks (CNN) and the visual recognition with the infrastructure of TensorFlow and GPUs. Particularly, we will study the language TensorFlow that enables its programs performing parallel computations on GPUs. Students will learn from the practice implementation on artificial neural networks techniques, including CNN, Recurrent Neural Networks, Generative Models, and deep reinforcement learning. At the end of this course, students should gain: (1) the general knowledge on artificial neural networks methodologies, algorithms and implementation, and (2) the hands-on system development experience on programs with TensorFlow and GPU.

    每周課程進度與作業要求 Course Schedule & Requirements

    週次

    課程內容與指定閱讀

    教學活動與課前、課後作業

    學生每週學習投入時間

    (含課堂教學時數)

    1

     

    Course Introduction of ANN

    閱讀講義閱讀 cs231n_2019_lecture01

    8 hrs/

    2

    Computer vision overview (cs231n.stanford.edu/2019/Lecture 1)

    閱讀講義閱讀 cs231n_2019_lecture01、做作業

    3

    Image Classification (cs231n.stanford.edu/2019/Lecture 2)

    閱讀講義閱讀 cs231n_2019_lecture02、做作業

    4

    Loss Functions and Optimization (cs231n.stanford.edu/2019/Lecture 3)

    閱讀講義閱讀 cs231n_2019_lecture03、做作業

    5

    Introduction to Neural Networks (cs231n.stanford.edu/2019/Lecture 4)

    閱讀講義閱讀 cs231n_2019_lecture04、做作業

    6

    Convolutional Neural Networks (cs231n.stanford.edu/2019/Lecture 5)

    閱讀講義閱讀 cs231n_2019_lecture05、做作業

    7

    Deep Learning Hardware and Software (cs231n.stanford.edu/2019/Lecture 6)

    閱讀講義閱讀 cs231n_2019_lecture06、做作業

    8

    Training Neural Networks, part I (cs231n.stanford.edu/2019/Lecture 7)

    閱讀講義閱讀 cs231n_2019_lecture07、做作業

     

    9

    期中報告與檢討

     

    10

    Training Neural Networks, part II (cs231n.stanford.edu/2019/Lecture 8)

    閱讀講義閱讀 cs231n_2019_lecture08、做作業

    11

    CNN Architectures (cs231n.stanford.edu/2019/Lecture 9)

    閱讀講義閱讀 cs231n_2019_lecture09、做作業

    12

    Recurrent Neural Networks (cs231n.stanford.edu/2019/Lecture 10)

    閱讀講義閱讀 cs231n_2019_lecture10、做作業

    13

    Generative Models (cs231n.stanford.edu/2019/Lecture 11)

    閱讀講義閱讀 cs231n_2019_lecture11、做作業

    14

    彈性授課

    參訪或自行閱讀 cs231n_2019_lecture12、做作業

    15

    彈性授課

    參訪或自行閱 cs231n_2019_lecture13、做作業

    16

    Deep Reinforcement Learning (cs231n.stanford.edu/2019/Lecture 14)

    閱讀講義閱讀 cs231n_2019_lecture14、做作業

    17

    期末報告與檢討

     

    18

    期末報告與檢討

     

     

           
         
         
         
         
         
         
         
           
         
         
         
         
         
         
         
         
         
     

     

     

    授課方式Teaching Approach

    50%

    講述 Lecture

    20%

    討論 Discussion

    20%

    小組活動 Group activity

    10%

    數位學習 E-learning

    0%

    其它: Others:

    評量工具與策略、評分標準成效Evaluation Criteria

    Weekly meeting attendance (1% x 18) 18%

    Meeting participation 36%

    Group peer evaluation form 6%

    Term project deliverable 40%

    Total 100%

    指定/參考書目Textbook & References

    TBA

    已申請之圖書館指定參考書目 圖書館指定參考書查詢 |相關處理要點

    維護智慧財產權,務必使用正版書籍。 Respect Copyright.

    課程相關連結Course Related Links

    None

    課程附件Course Attachments

    課程進行中,使用智慧型手機、平板等隨身設備 To Use Smart Devices During the Class

    Yes

    列印