In the framework of the course, a comprehensive foundation will be provided in machine learning techniques. The first part of the course will focus on fundamental learning concepts and supervised learning algorithms. The second part will focus on clustering, and projection to low-dimensional spaces such as Principal Component Analysis (PCA), as well as additional topics like ensemble models, regularization, bootstrap, and an introduction to neural network models.
Machine learning (or Computational learning) is a sub-field in computer science and in Artificial Intelligence and intersects Statistics and Optimization theory. The field deals with algorithms, which allow computer to learn from examples, and to operate in a variety of computational tasks, where classical programming is impossible or not economical. Machine learning is relatively new area and is responsible to recent breakthroughs in Artificial intelligence, Data mining and automatic knowledge discovery in big data. In its core lies the ability to the specific tasks. This is done by analyzing large quantities of data, pattern recognition and forecasting future behavior.
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.
The computer science seminar on seminal papers in AI will explore the foundational research that has shaped the field of artificial intelligence. Participants will engage with groundbreaking works that introduced key concepts, algorithms, and methodologies, such as neural networks, machine learning, natural language processing, and reinforcement learning. Through presentations and discussions, attendees will gain a deeper understanding of the historical context, innovative ideas, and enduring impact of these pivotal papers on modern AI developments and applications. The seminar aims to foster critical thinking and inspire new perspectives on the future direction of AI research.
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.
This course aims to give the students a basic foundation in Artificial Intelligence (AI) techniques. The first part of the course will focus on fundamental AI concepts of Search & Planning. The second part will include Probabilistic reasoning. The theoretical material will be supported by examples and practical applications.