Aims

This module investigates how machine learning techniques can be applied to the analysis and synthesis of computer programs. A variety of machine learning techniques will be covered considering different applications such as program repair, code suggestion, summarisation and comment-generation. The module will be structured around students reading papers and reproducing some recent results from the literature.

Syllabus

• Session 1 (2hr): Introduction, summary of proposed papers for reimplementation. In later sessions students will produce a written project plan and make weekly written reports - this session will have a model example of each of these.
• Session 2 (2hr): Introductory lecture on deep learning models CNN, RNN, LSTM, python/tensorflow/pytorch practical.
• Session 3,4,5,6 (2hr): Weekly standup, students deliver 100-200 word summary of week's activity and plan for next week. Help session if needed. The summary for session 3 will be a plan for the whole project.
• Session 7 and 8 (2+2 hr): show and tell presentations, demo, brief writeup: what works well and what doesn't. 15 minute slots.

Objectives

On completion of this module, students should:

• gain a general familiarity with the state-of-the-art in this area;
• have investigated one particular technique in detail;
• have attempted to reproduce a research result from the literature.

Coursework

Students will deliver regular written reports of progress and a project writeup. Marks will also be assigned for the quality of the software written and the final presentation.

Assessment

1. written plan (10%)
2. weekly summary 1 (10%)
3. weekly summary 2 (10%)
4. weekly summary 3 (10%)
5. final presentation (20%)
6. project writeup (20%)
7. software deliverable (20%)

Recommended reading

TBC