3.66. AI266 AI for Software Engineering (Elective)

3.66. AI266 AI for Software Engineering (Elective)

Figure 3.65: Connection Map. AI266 AI for Software Engineering

3.66.1. Justification Back to top

This course integrates AI techniques into the software development lifecycle, covering practical applications like code generation, automated debugging, and system optimization through machine learning.

3.66.2. Generales Goals Back to top

  1. Implement MLOps pipelines in traditional development environments
  2. Design systems integrating AI models into software applications
  3. Evaluate ethical implications in development process automation

3.66.3. Contribution to Outcomes Back to top

AG-C09) Design and Development of Solutions: Designs, implements, and evaluates solutions for complex computing problems. (Usage)
AG-C12) Applies computer science theory and software development fundamentals to produce computer-based solutions. (Usage)

3.66.4. Content Back to top

3.66.4.1. AI-SE Fundamentals (12 hours) [Skills AG-C09,AG-C12] Back to top

Bibliography: (Zhang and Chen, 2022)

Topics

  1. Design patterns for AI-SE systems
  2. Hybrid system architectures (AI + traditional software)
  3. Quality metrics for intelligent components

Learning Outcomes

  1. Design software architectures incorporating AI components [Assessment]
  2. Evaluate trade-offs in hybrid systems [Usage]
3.66.4.2. Advanced Applications (24 hours) [Skills AG-C09,AG-C12] Back to top

Bibliography: (Allamanis et al., 2018; Chen et al., 2021)

Topics

  1. Automated code generation (Codex, CodeT5)
  2. Intelligent debugging
  3. Automated performance optimization

Learning Outcomes

  1. Implement AI-assisted code generation tools [Usage]
  2. Integrate recommendation systems into IDEs [Assessment]
3.66.4.3. Automation Ethics (8 hours) [Skills AG-C09,AG-C12] Back to top

Bibliography: (Zhang and Chen, 2022)

Topics

  1. Risks of automated code generation
  2. Biases in developer recommendation systems
  3. Legal liability in autonomous systems

Learning Outcomes

  1. Identify ethical critical points in AI-SE [Familiarity]
  2. Propose mitigation protocols [Usage]

3.66.5. Bibliography Back to top

Zhang, M. and Chen, S. (2022). AI Engineering: Applying AI in Software Development. O'Reilly.

Allamanis, M., Barr, E., Devanbu, P., and Sutton, C. (2018). A survey of machine learning for big code and naturalness. ACM Computing Surveys, 51(4).

Chen, Y., Liu, X., and Shi, Z. (2021). Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. In EMNLP.

Spotted a typo, an outdated course, a broken link, or have a suggestion? Let us know.

Scan to open on your phone