Week 8 – Recurrent Neural Networks (RNNs); Introduction

https://opencourse.inf.ed.ac.uk/MLP

Week 8

Teaching week commencing: 09-Nov-2026

Key topics: Recurrent Neural Networks (RNNs); Introduction

Reading guide

Goodfellow et al, chapter 10 (sections 10.1, 10.2, 10.3)

Optional Reading on RNNs: 

• T Robinson et al. “The use of recurrent networks in continuous speech recognition”, in Automatic Speech and Speaker Recognition – Advanced Topics (Lee et al (eds)), Kluwer, 233–258 (1996).
• T Mikolov et al. “Recurrent Neural Network Based Language Model”, Interspeech (2010).
• Sutskever, et al, “Sequence to sequence learning with neural networks.” NeurIPS2014.
   

Lecture materials

Scripted recording: Recurrent Neural Networks (1)

This recording was produced in a previous year. The corresponding lecture content has since changed significantly, so the recording should be treated as supplementary material. References to course logistics are out of date.

Slides: MLP 26-27 Recurrent Neural Networks; Introduction (see below)

Practical materials

Labs: Lab 7

Milestones: We can now handle sequences of data!

Expected Effort Estimate: 7 hours

• Attendance/Timed Events
• Lab - 1 hour
• Recordings - 1 hour
• Discussion/Lecture - 1 hour
• Study - 3 hours ( +1 hour for PyTorch Lab component)

"Study" can include extra time working on labs, suggested reading, and Piazza. The Labs (from Week 2 and on) are generally a good starting point as they also test your understanding of the material.

(Semester 1 Total Expected Effort <= 82 hours = 67 hours studying + max 15 hours coursework) [The University guidelines are 10 credits = 100 hours, so we plan for less to allow for a range of needs].