Introduction

Mon, 01 Jan 0001 00:00:00 +0000

Pengyu Nie

Agenda

Name: Pengyu Nie
Assistant Prof @ UWaterloo CS since 2023
- before that: PhD @ UTAustin ECE
- before that: BSc @ USTC Physics
2nd time teaching this course
Research interests on AI + SE, recent focus:
- AI-assisted test generation and maintenance
- Automating MLE (machine learning engineering)
- Efficient model architectures for SE
- … find out more in this course

The course website: https://pengyunie.github.io/cs846mlse-1265/
- Course logistics, syllabus, slides
Email: pynie@uwaterloo.ca
- Project milestone submissions
- Announcements
- General questions

Week 1, 05/12
- Introduction and planning
Week 2, 05/19
- Lecture: software engineering essentials (intro, program analyses, other artifacts, platforms & mining sources)
Week 3, 05/26
- No class, please attend Kyunghyun Cho’s talk
Week 4, 06/02
- Lecture: machine learning essentials (large language models, transformers, agents, etc.)
Week 5, 06/09
- Project idea/proposal discussions
Week 6 – Week 12: seminar/presentation (led by you), guest lectures, etc.

Typical class structure starting from Week 6:

Mon, 01 Jan 0001 00:00:00 +0000

Pengyu Nie

Goals
- review key concepts in SE from data-driven view
- pointers to tools and datasets
- breath; relevancy; recency
No-Goals
- depth; completeness

some are readily available in verbatim form (code)
some need to be extracted by parsing (call graph) or executing (data flow) code
some need to be connected with other artifacts to make sense (comment-code, test-code)

public class C {
 public int factorial(int n) {
 if (n > 0) {
 return n * factorial(n - 1);
 } else {
 return 0;
 }
 }
}

Basis of the compilation pipeline, produce a stream of PL tokens for downstream analyses
PL tokens ≠ ML tokens (by subword tokenizers like BPE/SentencePiece), e.g., factorial vs fact|orial.

public class C {
 public int factorial(int n) {
 if (n > 0) {
 return n * factorial(n - 1);
 } else {
 return 0;
 }
 }
}