Type of Credit: Elective
Credit(s)
Number of Students
The course objective is the introduction of Convolutional Neural Networks and the visual recognition with the infrastructure of Tensorflow and GPUs.
能力項目說明
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.
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/週 |
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 |
參訪或自行閱讀 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 |
|
|
|
Weekly meeting attendance (1% x 18) 18%
Meeting participation 36%
Group peer evaluation form 6%
Term project deliverable 40%
Total 100%
TBA
None