Pattern Recognition and Machine Learning, 5 op

Ydinsisältö

• Statistical Signal Processing: Estimation theory; Maximum likelihood; Estimation of signal parameters (e.g., phase, amplitude and frequency).
• Detection theory; Receiver Operating Characteristics; Neyman-Pearson decision rule and relation to machine learning.
• Linear models: regression and classification, support vector machines, logistic regression, regularization.
• Modern tools: Random forests, Bagging, Boosting, Stacking, Deep Learning
• Performance evaluation, cross-validation, bootstrapping
• Implementations in Python: 1) Scikit-learn, 2) Tensorflow