Initially, the problems that arise when you want to process natural language will be reviewed. Next, language models will be introduced. Later, central algorithms such as IT-IDF, WORD2VEC, Bag of words, POS and more will be reviewed. At the same time, we will learn how to implement language processing algorithms using Python and dedicated libraries. Key applications in language processing will be reviewed: summarization, translation and keyword, sentiment analysis and more. The principles of LLM will be taught, including TRANSFORMERS, VAE and the use of language models and libraries such as GPT, HUGGINGFACE and more.
As part of the course, the student will be exposed to all the development stages of an application or software package including: application design and development, interface design, algorithm implementation, architecture selection and database integration, methodology implementation, critical thinking, end-to-end development and testing, documentation and presentation, teamwork and project management.
This is a continuation course in which the student will be exposed to all the development stages of an application or software package, including: application design and development, interface design, algorithm implementation, architecture selection and database integration, methodology implementation, critical thinking, end-to-end development and testing, documentation and presentation, teamwork and management projects.
The course presents algorithms and advanced methods in machine learning, most are Bayesian-based methods. The course starts with a presentation of a few basic algorithms used for graphical models. We will learn how to compute a-posterior probabilities of hidden variables, present a universal-type algorithm known as the ‘sum-product’ algorithm for the computation of marginal distributions in complex graphs. We will extend the notion graphs to Markov Random Fields, and show some of its uses for example in computer vision. We will then investigate the case where there are no clear parameters for the model. We will describe Gaussian and Dirichlet processes and show some examples such as the problem of clustering where there is no a-priori number of clusters. Bayesian methods sometimes force us to evaluate integrals using sampling methods, in particular where such integrals have no analytic closed form. We will discuss some basic Monte Carlo sampling methods. The course also deals with cases where based on the data given we are asked to choose a model. We will discuss some Bayesian methods or alternatively hyper-parameter optimization to find an appropriate model. In addition the course will present some dimension reduction methods, their advantages and limitations. Moreover we will discuss semi-supervised methods where only part of the data is annotated. The course ends with an introduction to the theory of genetic algorithms.