Selected Topics in Artificial Intelligence 1 / Large language models: machine learning view
The course presents large language models (LLMs) from the point of view of machine learning, covering the main ideas used in their creation, adaptation, and application. In this context, it presents advanced machine learning topics used in representation learning, including topics from ensemble learning, explainable artificial intelligence, transfer learning, and graph learning. The contents commonly apply in natural language processing, natural language understanding, knowledge graphs, multi-relational learning, digital humanities, bioinformatics, etc. The specific technical contents of the course cover neural network architectures for large language models, relevant large language model adaptions and extensions, retrieval augmented generation, and multimodal models. The course requires students to apply large language models, typically to language and graph processing tasks, preferably in the context of their research work.
