理工学研究科Graduate School of Science and Engineering
COS500X3(計算科学 / Computational science 500)ニューラルネットワークの理論と応用Theory and Applications of Neural Networks
孫 鶴鳴Heming SUN
授業コードなどClass code etc
学部・研究科Faculty/Graduate school | 理工学研究科Graduate School of Science and Engineering |
添付ファイル名Attached documents | |
年度Year | 2022 |
授業コードClass code | YB038 |
旧授業コードPrevious Class code | |
旧科目名Previous Class title | |
開講時期Term | 秋学期授業/Fall |
曜日・時限Day/Period | 月3/Mon.3 |
科目種別Class Type | |
キャンパスCampus | 小金井 |
教室名称Classroom name | 各学部・研究科等の時間割等で確認 |
配当年次Grade | |
単位数Credit(s) | 2 |
備考(履修条件等)Notes | |
実務経験のある教員による授業科目Class taught by instructors with practical experience | |
カテゴリーCategory | 応用情報工学専攻 |
すべて開くShow all
すべて閉じるHide All
Outline (in English)
The course is composed of the theory and implementation of neural networks.
The learning objective is to understand the principles of neural networks and have the ability to solve some computer vision and signal processing problems by using neural networks.
Learning activities outside of classroom is about one hour per class.
Grading criteria is mainly based on the project and presentation.
授業で使用する言語Default language used in class
英語 / English
授業の概要と目的(何を学ぶか)Outline and objectives
The course is composed of the theory and implementation of neural networks.
The learning objective is to understand the principles of neural networks and have the ability to solve some computer vision and signal processing problems by using neural networks.
Learning activities outside of classroom is about one hour per class.
Grading criteria is mainly based on the project and presentation.
到達目標Goal
There are three major goals.
1) Understand the basic principles of neural networks.
2) Command at least one training framework such as Tensorflow.
3) Can solve one computer vision or signal processing research problems by using neural networks.
この授業を履修することで学部等のディプロマポリシーに示されたどの能力を習得することができるか(該当授業科目と学位授与方針に明示された学習成果との関連)Which item of the diploma policy will be obtained by taking this class?
ディプロマポリシーのうち、「DP1」「DP2」「DP3」に関連
授業で使用する言語Default language used in class
英語 / English
授業の進め方と方法Method(s)(学期の途中で変更になる場合には、別途提示します。 /If the Method(s) is changed, we will announce the details of any changes. )
There are 12 lectures for the explanation and exercise, two lectures for the presentation.
Classes could be online. Changes in the lecture plan due to this shift will be announced on the learning support system.
アクティブラーニング(グループディスカッション、ディベート等)の実施Active learning in class (Group discussion, Debate.etc.)
あり / Yes
フィールドワーク(学外での実習等)の実施Fieldwork in class
なし / No
授業計画Schedule
授業形態/methods of teaching:オンライン/online
※各回の授業形態は予定です。教員の指示に従ってください。
1[オンライン/online]:History of Neural Networks
This course introduces the the history and inspiration of neural networks.
2[オンライン/online]:Training the Network
This course explains some basic knowledge for training the network.
3[オンライン/online]:Improve the Learning I
This course explains the training techniques such as cost function determinations.
4[オンライン/online]:Improve the Learning II
This course explains the training techniques such as regularization methods.
5[オンライン/online]:Convolutional Neural Network
This course introduces the structure and benefit of convolutional neural networks.
6[オンライン/online]:Variants of Convolutional Neural Network
This course introduces several kinds of convolutions such as transposed convolution.
7[オンライン/online]:Popular Convolutional Neural Network Architectures
This course introduces some recent famous CNN architectures such as AlexNet.
8[オンライン/online]:Reducing Complexity of Convolutional Neural Network
This course introduces some simplified CNN such as 1x1 convolution.
9[オンライン/online]:Advanced Convolutional Neural Network
This course introduces some advanced CNN such as group convolution.
10[オンライン/online]:Recurrent Neural Networks
This course explains some RNNs such as Long-Short Term Memory (LSTM).
11[オンライン/online]:Variational Autoencoder and Generative Adversarial Network
This course explains the principles of VAE and GAN and their usage in image generation.
12[オンライン/online]:Transfer Learning
This course shows how to use transfer learning in different networks.
13[オンライン/online]:Final Presentation I
Students give presentation.
14[オンライン/online]:Final Presentation II
Students give presentation.
授業時間外の学習(準備学習・復習・宿題等)Work to be done outside of class (preparation, etc.)
【本授業の準備・復習時間は、各4時間を標準とします。】Every 3-4 classes, there is a report.
テキスト(教科書)Textbooks
教科書を使用しない
参考書References
参考書を指定しない
成績評価の方法と基準Grading criteria
Report: 40%
Attendance: 10%
Final project presentation: 50%
学生の意見等からの気づきChanges following student comments
特になし
学生が準備すべき機器他Equipment student needs to prepare
A notePC