学部後期課程
HOME 学部後期課程 Data Science and Machine Learning
過去(2020年度)の授業の情報です
学内のオンライン授業の情報漏洩防止のため,URLやアカウント、教室の記載は削除しております。
最終更新日:2024年3月15日

授業計画や教室は変更となる可能性があるため、必ずUTASで最新の情報を確認して下さい。
UTASにアクセスできない方は、担当教員または部局教務へお問い合わせ下さい。

Data Science and Machine Learning

Data Science and Machine Learning
This course covers a range of methods in Data Science and Machine Learning, including Deep Learning in Artificial Neural Networks.

The topics will include: Data manipulation: dataset transformation, visualization, data cleaning, web data scraping. Supervised machine learning: under-fitting and over-fitting, regularization, cross-validation, data augmentation. Unsupervised machine learning: clustering, principal component analysis. Semi-supervised learning. Distributed data representation: entity embedding. Nonlinear dimensionality reduction. Computational graphs and functional programming. Practical aspects of high-performance computing: GPU computing, cloud computing.

The topics will also include some of following areas. The choice will be made based on the students' interests. Optimization: backpropagation, stochastic gradient descent and its accelerated versions. Supervised and semi-supervised machine learning: details of regularization and data augmentation methods. Neural network architecture: activation functions and their properties, layer patterns. Training neural networks: data preprocessing, weight initialization, gradient flow, batch normalization, regularization, practical aspects of GPU computing and distributed training. Hyper-parameter optimization, model ensembles, model compression. Transfer learning and fine-tuning. Spatial data modeling: convolutional networks, visualizing their internal data representations, susceptibility to adversarial examples. Sequence data modeling: recurrent networks, LSTMs GRUs, and their convolutional alternatives, attention. Natural language processing: word embeddings, neural machine translation, transformer networks. Unsupervised machine learning: variational autoencoders, generative adversarial networks. Reinforcement learning: Q-learning, policy gradient methods.

The course will include a first introduction to Python and R, as well as PyTorch/FastAI and TensorFlow/Keras. For specialized tasks other software will be introduced. Students are encouraged to bring to the class their own datasets, which could then be used for the purposes of instruction and practical demonstration.
MIMA Search
時間割/共通科目コード
コース名
教員
学期
時限
0704245
FEC-EC5801L3
Data Science and Machine Learning
Fabinger Michal
A1 A2
月曜3限
マイリストに追加
マイリストから削除
講義使用言語
英語
単位
2
実務経験のある教員による授業科目
NO
他学部履修
開講所属
経済学部
授業計画
The schedule will be determined based on students' interests.
授業の方法
Class instruction and individual research projects.
成績評価方法
Evaluation criteria will include homework, class presentations, class participation and/or research projects.
教科書
-
参考書
-
履修上の注意
-