Lecture 3: Bayesian Decision Theory II
1. Bayes risk, Bayes error, and empirical error.
2. Two-state case.
3. ROC curve and PR curve.
Lecture notes Stat 231-CS276A,
Three key variables in Bayesian decision theory and their ca
Lecture 2: Bayesian Decision Theory I
Bayesian decision theory is the basic framework for pattern recognition.
1. Diagram and formulation
2. Bayes rule for inference
3. Bayesian decision
4. Discriminant functions and space partition
5. Advanced i
Dimension reduction techniques
Common techniques for dimension reduction.
1. Principal component analysis (PCA): [ generative, global, linear ]
2. Fisher linear discriminant analysis: [ discriminative, global, linear ]
3. Independent component an
Lecture 5-6: MDS, LLE, Intrinsic dimensions
MDS is a technique motivated by 2-problems in understanding data in high dimensional spaces.
Its objective is to project an ensemble of data points into 1, 2, or 3-dimensional spaces so
Lecture 7-9. AdaBoost, RealBoost, and Logistic Regression
Boosting: One of a few popular machine learning algorithms in last 15
years (the others are Support Vector Machines, and DeepLearning).
It has several versions:
Adaboost, RealBoost, and LogitBoost
Pattern Recognition and Machine Learning
Lecture note, Stat231-CS276A,
Recent advances in PRML
IBM Watson for Jeopardy
1, Understand human speech
2, Search and evaluates hypotheses
Google driverless car
Still many obstacles remain