At the conclusion of course students are able to:
- Understand the basic principles of machine learning techniques and AI.
- Understand to implement the supervised and unsupervised machine learning algorithms.
Program Objectives
To acquire basic knowledge in machine learning techniques and learn to apply the techniques in the area of pattern recognition and data analytics.
About the Course
Artificial Intelligence (AI) is a research field that studies how to realize the intelligent human behaviours on a computer. The ultimate goal of AI is to make a computer that can learn, plan, and solve problems autonomously. Although AI has been studied for more than half a century, we still cannot make a computer that is as intelligent as a human in all aspects. However, we do have many successful applications. In some cases, the computer equipped with AI technology can be even more intelligent than us. The Deep Blue system which defeated the world chess champion is a well-known example.
In this course, we will study the most fundamental knowledge for understanding AI. We will introduce some basic search algorithms for problem solving; knowledge representation and reasoning; pattern recognition; and neural networks.
UNIT 1: INTRODUCTION
Introduction to Artificial Intelligence, AI problems, Applications of AI, Introduction to Natural Language Processing and Expert System, Machine Learning, types of machine learning, examples. Supervised Learning: Learning class from examples, learning multiple classes, regression, model selection and generalization, Parametric Methods: Introduction, maximum likelihood estimation, evaluating estimator, Bayes’ estimator, parametric classification.
UNIT 2: DIMENSIONALITY REDUCTION
Introduction, subset selection, principal component analysis, factor analysis, multidimensional scaling, linear discriminant analysis.
CLUSTERING
Introduction, mixture densities, k-means clustering, expectation-maximization algorithm, hierarchical clustering, choosing the number of clusters. Non-parametric: introduction, non-parametric density estimation, non-parametric classification.
MULTILAYER PERCEPTRON
Introduction, training a perceptron, learning Boolean functions, multilayer perceptron, backpropagation algorithm, training procedures.
UNIT 3: KERNEL MACHINES
Introduction, optical separating hyperplane, v-SVM, kernel tricks, vertical kernel, defining kernel, multiclass kernel machines, one-class kernel machines.
BAYESIAN ESTIMATION
Introduction, estimating the parameter of a distribution, Bayesian estimation, Gaussian processes.
UNIT 4: HIDDEN MARKOV MODELS
Introduction, discrete Markov processes, hidden Markov models, basic problems of HMM, evaluation problem, finding the state sequence, learning model parameters, continuous observations, HMM with inputs, model selection with HMM. Correlation and regression: Linear regression, Rank correlation, Method of least squares Fitting of straight lines and second-degree parabola. Linear regression and correlation analysis.
UNIT 5: REINFORCEMENT LEARNING
Introduction, single state case, elements of reinforcement learning, temporal difference learning, generalization, partially observed state.
REFERENCES
Introduction, single state case, elements of reinforcement learning, temporal difference learning, generalization, partially observed state.
- Alpaydin, Introduction to Machine Learning. 2nd MIT Press, 2009.
- P. Murphy, Machine Learning: A Probabilistic Perspective. MIT Press, 2012.
- Harrington, Machine Learning in Action. Manning Publications, 2012
- M. Bishop, Pattern Recognition and Machine Learning. Springer, 2011.
- Artificial Intelligence, Elaine Rich, Kevin Knight, Shivashankar B Nair, 3rdedition, McGraw Hill, 2009
