Courses

עיבוד שפה טבעית (10247)

Abstract:

The course will begin with an overview of the core challenges involved in natural language processing. This will be followed by an introduction to language models. Next, students will explore key algorithms such as TF-IDF, Word2Vec, Bag of Words, POS tagging, and others. In parallel, students will learn how to implement NLP algorithms in Python using dedicated libraries. The course will then cover major NLP applications, including summarization, translation, keyword extraction, and sentiment analysis. Students will also learn the foundations of LLMs, including Transformers and VAEs, along with practical use of language models and libraries such as GPT and Hugging Face. By the end of the course, students will be familiar with common embedding methods and the principles behind attention layers, RAG, fine-tuning, agent creation, and evaluating language model quality using a variety of metrics.

פרויקט גמר למדעים1 (11402)

Abstract:

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.

פרויקט גמר למדעים2 (11403)

Abstract:

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.

עיבוד שפות טבעיות ודיבור (65007)

Abstract:

The course presents the theoretical and practical foundations of modern Natural Language Processing. We will begin with text representation, tokenization, language models, embeddings, and classical methods for text classification and retrieval. We will then study neural language models, Attention, and the Transformer architecture, which forms the basis for large language models such as GPT and BERT.

The course emphasizes contemporary applications of large language models, including prompting, instruction following, model adaptation using PEFT/LoRA, the construction of Retrieval Augmented Generation systems, and the use of Agents that operate external tools.

In addition, the course will cover the evaluation of NLP and LLM systems using a variety of metrics, including BLEU, ROUGE, Perplexity, BERTScore, Precision@k, Faithfulness, and Task Success.

The course combines theoretical lectures, hands-on Python exercises, paper analysis, and practical examples from industry. By the end of the course, students will complete a practical project involving the construction, adaptation, and evaluation of an NLP/LLM system.

מבוא למידה עמוקה (65021)

Abstract:

During the course, the students will learn advanced methods of machine learning for feature extraction, methods for dimensionality reduction, etc.