SYLLABUS - machine learning
Lectures: 102 16:00-20:00, Wednesday - 1st Sem.
- Course Description. Machine Learning (ML) is the design of a system that can learn from data. This course covers the advanced topics of ML such as Data Preprocessing, Ensemble Learning, Parallelizing Neural Network Training with Theano, and Deep Belief Network.
- Coursework. Coursework will consist of weekly homework, quizzes , midterm, and a final exam. The overall grade will be determined %10 from class activity, 10% for each quiz, 10% from midterm, and 60% from the final exam.
- Exam policy. No collaboration is permitted during the exam . If any collaboration with the intention of copying is caught, the student will get a failing grade.
- Smartphone policy. Smartphones are not allowed during lectures.
- Text. The course textbook is "Python Deeper Insights into Machine Learning", 1st Edition, by Sebastian Raschka, David Julian, John Hearty
- Week 1
- Giving Computers the Ability to Learn from Data
- Training Machine Learning Algorithms for Classification
- Week 2
- A Tour of Machine Learning Classifiers Using Scikit-learn
- Building Good Training Sets – Data Preprocessing
- Week 3
- Compressing Data via Dimensionality Reduction
- Learning Best Practices for Model Evaluation and Hyperparameter Tuning
- Week 4
- Combining Different Models for Ensemble Learning
- Applying Machine Learning to Sentiment Analysis
- Week 5
- Embedding a Machine Learning Model into a Web Application
- Predicting Continuous Target Variables with Regression Analysis
- Week 6
- Working with Unlabeled Data – Clustering Analysis
- Training Artificial Neural Networks for Image Recognition
- Week 7
- Parallelizing Neural Network Training with Theano
- Thinking in Machine Learning
- Week 8
- Tools and Techniques
- Turning Data into Information
- Week 9
- Models – Learning from Information
- Linear Models
- Week 10
- Neural Networks
- Features – How Algorithms See the World
- Week 11
- Learning with Ensembles
- Design Strategies and Case Studies
- Week 12
- Unsupervised Machine Learning
- Deep Belief Networks
- Week 13
- Stacked Denoising Autoencoders
- Convolutional Neural Networks
- Week 14
- Semi-Supervised Learning
- Text Feature Engineering
- Ensemble Methods
- Additional Python Machine Learning Tools