teaching

Deep Learning

Course Description

In this course, the following topics are covered in the area of deep learning: Neural Networks and Convolutional Neural Networks, Optimization and Regularization, Supervised and Unsupervised Methods, Discriminative Networks, Training of Networks, Deep Generative Networks, Adversarial methods, Classification applications, Recurrent Neural Networks, Attention Mechanism and Transformers, Temporal Prediction applications The specific aims of the course are:
  1. To introduce main techniques in Deep Learning
  2. To understand the mathematical principles of optimization and regularization of deep learning methods
  3. To be able to design deep neural networks for various problems in artificial intelligence
  4. To implement solutions to learning problems using various deep neural network techniques

3D Vision

Course Description

The aim of the course is:
  1. To introduce main problems in 3D Computer Vision
  2. To learn main techniques in analysis and modeling of 3D vision problems. Those will aid in extracting and understanding the 3D structure in the scenes using the observations in the form of multiple 2D or 3D images.
  3. To study the 3D vision techniques in terms of both mathematical principles and computer realizations as well as applications

Computer Vision

Course Description

The aim of the course is to study computer vision, which tries to make compu ters see and interpret using the observations in the form of multiple 2D (or 3D) images. In this undergraduate level course, the focus is on mainly 2D image processing fundamentals and basic computer vision concepts. The course will provide the participants with a background in Computer Vision both in practical aspects as being able to implement computer vision algorithms, and their mathematical understanding.

Probability & Statistics for Data Science

Course Description

Upon successful completion of YZV231E, students are expected to be able to:
 1. Define laws and axioms of probability and be able to work with set theoretical rules of events and probabilities and concept of independence
 2. Construct probabilities and conditional probabilities; use them in Bayes law to model simple real life problems
 3. Know and utilize random variables (r.v.s), important standard models of probability density functions (pdfs) and cumulative density functions in both continuous and discrete space
 4. Express multiple r.v.s with joint pdfs, relating to marginal pdfs and conditional pdfs, as well as to concepts of independence and correlatedness
 5. Estimate means, variances, covariances, moments of random variables and random vectors
 6. Calculate best predictors in minimum mean squared sense both for linear and nonlinear predictors
 7. Know the meaning and implications of limit theorems : Law of large numbers and Central limit theorem
 8. Define and Utilize Basic Bayesian Statistical Inference Techniques and Classical Statistical Inference Techniques including Hypothesis Testing, Parameter Estimation, Linear Regression and Significance Testing.
 9. Implement the above concepts in a programming environment (PYTHON)

Signal & Systems for Comp. Eng.

Course Description

The aim of the course:   Classification of signals, basic signals, classification and properties of systems, time domain characterization of Linear Time Invariant (LTI) systems, Continuous - Time and Discrete - Time Fourier Series, Continuous - Time and Discrete - Time Fourier Transforms, frequency domain characterization of Linear Time Invariant (LTI) systems, Sampling.