## About

**Prerequisite: **Linear Algebra, Statistics and Probability, Python (or MATLAB)

Skip to content## About

## Instructor

Go to Top

Machine learning is a subset of artificial intelligence that empowers computers to learn from data and improve over time without explicit programming. By utilizing various algorithms and statistical models, machine learning systems can identify patterns and make predictions or decisions. Its applications span across numerous fields, including but not limited to healthcare, finance, retail, and cybersecurity. In healthcare, machine learning aids in diagnosis, treatment optimization, and drug discovery. In finance, it assists in fraud detection, risk assessment, and algorithmic trading. Retailers use machine learning for personalized recommendations and demand forecasting, while cybersecurity relies on it for threat detection and prevention. Overall, machine learning revolutionizes industries by automating tasks, enhancing efficiency, and extracting valuable insights from vast datasets.

**Prerequisite: **Linear Algebra, Statistics and Probability, Python (or MATLAB)

**Associate professor**

Department of Electrical Engineering, Control Systems

Member of APAC research group

K. N. Toosi University of Science and Technology

**Introduction**

Examining the basic concepts of machine learning and its types, machine learning as a classifier, identifier, predictor, Cluster, etc.

**Regression**

Examining the basic concepts of regression, more training and evaluation of learning systems, least squares regression, gradient descent, least squares regression, logistic regression

**Classification and linear classifier**

Concepts of classification, perceptron, multi-class classification and classification based on Least squares, Bayes decision theory, Bayes classification, probability density function estimation by parametric equality method, and non-parametric

**Dimensional reduction**

Linear dimensional reduction methods, unsupervised, unsupervised PCA, LDA, introduction to non-linear dimensional reduction

**Support vector machine**

Linear separator with maximum margin, support vector, smooth margin, kernel

**Neural networks**

Basic definitions, physiological concepts, what is a neuron? Neuroscience and its development, neuron models, Mathematical models, linear classifier, the structure of the neural network, communication between neurons, communication ability of neurons,

Applications, multilayer perceptron network, optimization, nonlinear classifier, identifier and..

**Example-based learning**

Features, IBL, KNN method and its types, RBF method, example-based inference, transition to the story of Fuzzy! Basics of fuzzy system, fuzzy sets, if-then rules, fuzzy logic, fuzzy inference, fuzzy rule base, fuzzy system components, nonlinear mapping fuzzy system, application of fuzzy system, fuzzy control, TSK and structure systems, ANFIS (Applications: pattern recognition)

**Decision tree**

Introduction, review of decision tree and some of its types, middle node, branch and leaf, algorithm, ID3 entropy, Problems, and advantages, pruning the decision tree

**Combination of classifiers**

Review of various methods of combination of classifiers, voting, AdaBoost, Boosting, Bagging

**Reinforcement learning**

Characteristics of reinforcement learning, Q learning algorithm

**Optimization**

Preliminary definitions, methods based on gradients, methods based on population, evolutionary optimization, algorithm genetics

- Tom Mitchell, “Machine learning”, McGraw Hill, 1997.
- Christopher M. Bishop, “Pattern Recognition and Machine Learning (Information Science and Statistics)”, Springer, 2006.
- S. Theodoridis and K. Koutroumbas, “Pattern recognition”, Fourth Edition, Academic Press, 2009.
- K. Murphy, “Machine Learning: A Probabilistic Perspective”, MIT Press, 2012.
- Martin T Hagan, Howard B Demuth, Mark H Beale, Orlando De Jesús, “NEURAL NETWORK DESIGN”, 2nd Edition, 2014.
- Li-Xin Wang, “A Course in Fuzzy Systems and Control”, Prentice Hall; 1st Edition, 1996.