Introduction to Python Programming
This course will give a practical introduction into programmatic thinking, algorithms and problem solving using the Python programming language as a vehicle.
INFO 4275 - Advanced Information Retrieval
Information retrieval is a field concerned with the structure, analysis, organisation, storage, searching, and retrieval of information. We will discuss advanced aspects of these topics, focusing on recent state-of-the-art developments that have been made, especially concerning neural models. Particular attention will be paid to different classes of neural rankers and how they compare in terms of their effectiveness at ranking and their efficiency. The module will be evaluated in terms of a small research project and an oral exam, which we will prepare for throughout the module with in-class discussion sessions.
MEDZ4610 - LLM-Assisted Cohort Discovery in Clinical Trials
The advances made by Large Language Models (LLMs) in Natural Language Processing (NLP) tasks, has renewed interest in many biomedical tasks, including that of clinical trial and patient matching. The seminar covers current research topics in the field of generative AI and its application in clinical trial matching. Students are introduced to the basics through lectures. They then present a paper and discuss its merits, challenges and future opportunities.
INFO 4271 - Modern Search Engines
Search engines are the main interface between people and humankind's massive globally distributed repositories of knowledge. In this practice-focused course, we will review information retrieval basics such as web crawling, content indexing, index compression, query processing, and result ranking, before moving on to advanced techniques for personalization, (dense) neural retrieval, and stochastic ranking. The capstone to this class will be a practical project in which students design and build their own search engines that will be evaluated in a retrieval competition.
INFO 4193 - Natural Language Processing
Natural Language Processing (NLP) is a sub-field of artificial intelligence that aims at understanding and automatic generation of texts for various applications, such as document classification, sentiment analysis, text summarization, speech recognition, etc. This course covers NLP topics including n-gram models, word embeddings, bag of word representations for document classification, classifiers, tokenization, part of speech tagging, matrix factorization and topic modeling, deep learning for language processing, transformers, language models and text generation, and finally applications such as document summarization, machine translation, or question answering.
Understanding Large Language Models
We will look (among others) at LLM architecture, training & fine-tuning, prompting, mechanistic interpretability of LLMs, LLM agents and different evaluation methods. Participants will be offered both a technical perspective and encouraged to critically think about important topics relevant to cognitive science and society in the context of LLMs.