Machine Learning 2025 Spring

21

新增“欲加簽的同學如果加簽沒上的話，是否要轉為旁聽 (未填寫者預設為否)”，如果有這個需求的同學可以上去修改表單回覆

星期五 (14:20~18:20) 博理112

The information here is tentative and subject to change. Please read the requirement of each homework before deadline.

You should NOT plagiarize, if you use any other resource, you should cite it in the reference.
You should NOT modify your prediction files manually.
Do NOT share codes or prediction files with any living creatures.
Your HW grade will be 0 if you violate any of the above rules first time (within a semester).
Your final grade x 0.9 if you violate any of the above rules first time (within a semester).
Your will get F for the final grade if you violate any of the above rules multiple times (within a semester).
Prof. Lee & TAs preserve the rights to change the rules & grades.

#	Date	Topic	Code	Platform	Deadline (UTC+8)	Prerequisite
x	2/21	Colab and Kaggle Tutorial		N/A	N/A	N/A
x	2/21	PyTorch Tutorial	N/A	N/A	N/A	N/A
HW 1	2/21	AI Agent1 -- RAG
HW 2	3/7	AI Agent2
HW 3	3/14	Understand Transformer
HW 4	3/21	Pre-training"LLM"
HW 5	3/28	Fine tune is powerful
HW 6	4/18	Fine-tuning leads to Forgetting
HW 7	5/2	RLHF
HW 8	5/9	Model Editing
HW 9	5/16	Model Merging
HW 10	5/23	Diffusion

* 請同學來信務必依照正確寄信格式，並請善用NTU Cool討論區