Scribd
Upload
45 views

Syllabus

This document provides a syllabus for a course on fundamentals and applications of generative artificial intelligence. The course will cover basics of natural language processing and generative models, including BERT, GPT, diffusion models, and GANs. It will also cover applications of generative AI in text, speech, images, and code generation. The course is taught by Hung-Yu Kao and includes lectures, tutorials, homework assignments, and a term project.

Uploaded by

伯阿
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
45 views

Syllabus

This document provides a syllabus for a course on fundamentals and applications of generative artificial intelligence. The course will cover basics of natural language processing and generative models, including BERT, GPT, diffusion models, and GANs. It will also cover applications of generative AI in text, speech, images, and code generation. The course is taught by Hung-Yu Kao and includes lectures, tutorials, homework assignments, and a term project.

Uploaded by

伯阿
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 11

Fundamentals and Applications of Generative AI

Syllabus
Hung-Yu Kao (高宏宇)
• 成功大學資訊工程系特聘教授
• 成功大學電機資訊學院副院長
• 中華民國 人工智慧學會 常務監事
• 中華民國 計算語言學會 理事長
• 人工智慧學校講師

Data Competition Award


• BioCreative, Rank 1, 2010, 2011, 2015
• TREC Blog, Rank 3, 2010
• ACL SemEval Rumor Detection Competition, Score Rank1, 2017
• ACL SemEval Argument Reasoning Comprehension Test, Rank 2, 2018
• CIKM AnalyticCup Short Text Matching, Rank 2, 2018
• WSDM Fake News Classification, Rank 3, 2019
• ACL/Google AI Gender Bias for Natural Language Processing Rank 4, 2019
• WSDM Visual Question Answering Challenge, Rank 4, 2022

NLP related publication (2019-2021)


• ACL x 3, ACL workshop x 2, Coling x 2, AAAI x 1, AACL x 2, WSDM x 1, ACML x 1,

2
Generative Artificial Intelligence
Method Company

Image GAN, Stable Diffusion, NVIDIA (StyleGAN2), OpenAI (DALL-E, CLIP),


Transformer DeepMind (BigGAN), LeepMotion (Midjourney),
StabilityAI (Stable Diffusion)
Text GPT (Generative Pre- OpenAI (ChatGPT, GPT-4), Meta (LLaMA2),
trained Transformer) Google (T5, XLNet, PaLM),

Speech GAN, VAE Google (WaveNet), OpenAI (WaveGlow)

Code Seq2Seq, GPT OpenAI (Copilot)

3
生成對抗網路 (Generative Adversarial Network，GAN）

https://github.com/jonbruner/generative-adversarial-networks/blob/master/gan-notebook.ipynb

4
Diffusion Model

5
Power of Image GAI
Training data generation / augmentation

Style transform

● Image compression
Super-resolution image

NIPS 2016 tutorial: http://auai.org/uai2017/media/tutorials/shakir.pdf


6
Power of Image GAI

NIPS 2016 tutorial: http://auai.org/uai2017/media/tutorials/shakir.pdf


7
In this course
Basics Not include
◦ Python usage ◦ Prompt usage

GAI
◦ NLP
◦ Generative Models
◦ Different Usages of GAI
Week Topics Cotent

Schedule W1 2/22
W2 2/29
Syllabus
TA Course: Python Tutorial Python, NumPy, Pandas, Scikit-learn (Homework 1)
Word Embeddings, Language Modeling (RNN), Sequence-to-sequence
W3 3/7 Introduction to AI (NLP)
Models, and Attention Mechanisms, Sub-word Tokenization; Transformers
W4 3/14 Introduction to Generative AI ELMo, BERT, GPT, and T5 (BERT and its Family) (Homework 2)
Lecture
W5 3/21 Introduction to Generative AI Decoding Strategies and Evaluations for Natural Language Generation
Tutorial
W6 3/28 TA Course: Pre-trained Language Model Tutorial PyTorch, T5, GPT-2 (Homework 3)
Reporting
Exam W7 4/4 Vacation

W8 4/11 Introduction to Generative AI GPT-3, InstructGPT, RLHF

W9 4/18 Introduction to Generative AI Parameter Efficient Fine-Tuning (PEFT)

W10 4/25 TA Course: LLM Tutorial OpenAI API Usage and Fine-tuning LLMs with LoRA (Homework 4)

W12 5/2 Image GAI (Prof. Hsu)

W12 5/9 Image GAI (Prof. Hsu)

W13 5/16 Image GAI (Prof. Hsu) (Homework 5)

W14 5/23 RAG (Prof. Chuang)

W15 5/30 RAG (Prof. Chuang) (Homework 6)

W16 6/6 Term Project

W17 6/13 Term Project

W18 6/20 Term Project


Grading

Homework
◦ single x 5~6 75 %
◦ group x 1 25% (from NCKUH/Law)
◦ #group members = 3 ~ 4
Instructors and TAs

§Instructors:
◦ Hung-Yu Kao 資訊系館 12F, Room 65C11 ([email protected])
◦ https://ikmlab.csie.ncku.edu.tw/advisor.html
§TAs:
§ 資訊系館 9F, Room 65903 IKM lab.
§ [email protected]

§Course website NCKU Moodle

You might also like