Meysam Madani

یادگیری ماشین و تشخیص الگو- میثم مدنی

Machine learning

Machine learning, a branch of artificial intelligence, concerns the construction and study of systems that can learn from data.

Course Materials

Homeworks: (In Scilab)

  • 1- Denoise an 200*200 image by histogram or sigmoid!
  • 2- Choose some functions and linear coefficients to fit and generate a dataset with some noise on it, then find linear coefficients!
  • 3-Generate a linear separable dataset in three class, then use fisher and least square method to find discriminant functions, plot all task you do.
  • 4- Please generate a two classes dataset with outlier, then use logistic, least square and fisher method for classifing data. Plot all you do. Also do all before for 4 classes data with outliers, which is not pitza like!

Deadlines:

  • Project Proposal 10 March 2014
  • Midterm 3 times,
  •    1- 13 March 2014,
  •    2- 4 May 2014,

    Chpater 1 and 2 (Distributions, Likelihood and applications),

    chapter 3 (regression, model selection, Scilab programming, lambda effects on loss functions, Bayesian Linear Regression, Predictive Distribution), chapter 4 (all i taught).

  •    3- 25 May 2014
  • Project 17 June 2014
  • Final Exam 17 June 2014

Pattern Recognition and Machin Learning(PRMLML)

Machine learning, a branch of artificial intelligence, concerns the construction and study of systems that can learn from data. For example, a machine learning system could be trained on email messages to learn to distinguish between spam and non-spam messages. After learning, it can then be used to classify new email messages into spam and non-spam folders.


The core of machine learning deals with representation and generalization. Representation of data instances and functions evaluated on these instances are part of all machine learning systems. Generalization is the property that the system will perform well on unseen data instances; the conditions under which this can be guaranteed are a key object of study in the subfield of computational learning theory.

 In this cource we concentrate on the following reference:

Christopher M. Bishop (2006) Pattern Recognition and Machine Learning, Springer

Course outline:

  • Scilab Programming
  • Probability Distributions
    Linear Models for Regression

        Linear Basis Function Models
        Bayesian Linear Regression
        Bayesian Model Comparison
    Linear Models for Classification
        Discriminant Functions
        Probabilistic Generative Models .
        Probabilistic Discriminative Models
        Bayesian Logistic Regression
    Neural Networks
        Feed-forward Network Functions
        Network Training
        Error Backpropagation
        The Hessian Matrix
        Regularization in Neural Networks
        Bayesian Neural Networks
    Kernel Methods
        Dual Representations
        Radial Basis Function Networks
        Gaussian Processes
    Sparse Kernel Machines
        Maximum Margin Classifiers
        Relevance Vector Machines
    Graphical Models
        Mixture Models and EM
        Conditional Independence