BIMSA > The Foundation of Large Language Models (LLMs) \(ICBS\)
The Foundation of Large Language Models (LLMs)
The large language models (LLMs) are reshaping our world. The basic knowledge of LLMs includes: language models, deep neural networks, attention mechanisms, Transformer models, etc. This course will provide a detailed explanation of the above knowledge and introduce the cutting-edge research and applications of large language models.
Professor Lars Aake Andersson
Lecturer
Hai Hua Xie
Date
25th March ~ 24th June, 2024
Location
Weekday Time Venue Online ID Password
Monday,Wednesday 13:30 - 15:05 A3-1-301 ZOOM 13 637 734 0280 BIMSA
Prerequisite
Computer Science, Machine Learning, Python
Syllabus
1. n-gram Language Model
2. Deep Learning
3. Neural Language Model
4. word2vec
5. Seq2seq-Attention
6. Transformers
7. BERT
8. GPT-2 and GPT-3
9. ChatGPT
10. Text2Image - Diffusion Model
11. Prompt Engineering
12. AIGC
Reference
[1] C. D. Manning, H. Schüte. 1999. Foundations of Statistical Natural Language Processing. The MIT Press.
[2] D. Jurafsky, and J. H. Martin. 2000.Speech and Language Processing, Prentice Hall, 2000（冯志伟，孙乐译，自然语言处理综论, 电子工业出版社）
[3] 冯志伟，自然语言处理的形式模型，中国科学技术大学出版社
[4] 宗成庆，统计自然语言处理(第2版)，清华大学出版社
Audience
Undergraduate , Advanced Undergraduate , Graduate
Video Public
Yes
Notes Public
Yes
Language
Chinese , English
Lecturer Intro
Dr. Haihua Xie receives a Ph.D. in Computer Science at Iowa State University in 2015. Before joining BIMSA in Oct. 2021, Dr. Xie worked in the State Key Lab of Digital Publishing Technology, Peking University from 2015-2021. His research interests include Natural Language Processing and Knowledge Service. He published more than 20 papers and obtained 7 invention patents. In 2018, Dr. Xie was selected in the 13th batch of overseas high-level talents in Beijing and was hornored as a "Beijing Distinguished Expert".