知能社会情報学講義Ⅴ

1. Class Guidance and System Environment Settings: - Python - Scikit-Learn - Numpy - Pandas - Matplotlib - TensorFlow 2. Basic Python (Part 1): - List, Tuple, Sets - String - Dictionary - If-Else Control Flow 3. Basic Python (Part 2): - Function - Classes - Reading and writing files: text file, CSV file, excel file 4. Working with Real Data - Gathering data - NumPy & Pandas - Preprocessing data: Standardization (Scaling), Encoding - Recursive Feature Elimination - Cross-validation - Evaluation Metrics 5. Supervised Learning - Traditional Classification & Regression: + Support Vector Machine (SVM) + Stochastic Gradient Descent + Nearest Neighbor + Naive Bayes + Decision Trees + Neural network models (supervised) - Ensemble Classification & Regression: + Boosting ensemble approach: Adaptive Boosting, Gradient Boosting + Average ensemble approach: Random Forests, Extra Trees, Bagging 6. Unsupervised Learning & Text Mining - Clustering: K-means, Neural network models (unsupervised) - Text Mining 7. Data Visualization - Matplotlib - Choosing the right graph - Plotting time-series data 8. Recommendation System - User-based Collaborative Filtering - Item-based Collaborative Filtering 9. Genetic Algorithms - Mutation - Crossover 10. Deep Learning Part 1 - Feed Forward Neural Network - Recurrent Neural Network (RNN) 11. Deep Learning Part 2 - Convolutional Neural Network (CNN) 12. Deep Reinforcement Learning - Deep Q-Learning 13. Wrapping Up/ Q&A

Online lecture and exercises

Final project report and attendance rate

None

None

Basic programming knowledge will be helpful but not strictly necessary.