Dr Dandan Zhang
ROBOTICS · AI · EDUCATION
IMPERIAL COLLEGE LONDON
Teaching & learning
Course resources, practical labs and study support.
ELEC70129 · Deep Learning
Learn deep learning through concepts, code and reproducible experiments. Course lead Dr Dandan Zhang · Postgraduate elective · 5 ECTS / 10 CATS.
Start here
Course overview · Course handbook (PDF) · Lab handbook (PDF)
Beginner code guide · Colab setup guide · All notebooks · Reading list
Approved GitHub access required. Sign in with an account authorised for the course repository. If a resource shows “404” after sign-in, contact the teaching team to check your access.
For current lecture slides, assessment instructions and deadlines, use the module’s official learning platform. Recommended books for independent study are listed below.
Core labs
Start with 00–03. GitHub access required.
00 Setup, tensors & training
Set up your environment and follow a training loop.
Notebook · Lab guide · Python
01 Convolutional neural networks
Explore convolution and image classification.
Notebook · Lab guide · Python
02 ResNet & residual blocks
Understand skip connections and residual learning.
Notebook · Lab guide · Python
03 RNN, GRU & LSTM
Build a foundation for modelling sequences.
Notebook · Lab guide · Python
Applications & next steps
Continue after the core labs. GitHub access required.
04 Image folders & datasets
Work with labelled image folders for classification.
Notebook · Lab guide · Python
05 Text sentiment
Apply sequence modelling to sentiment analysis.
Notebook · Lab guide · Python
06 ResNet transfer learning
Adapt a pretrained visual model to a new task.
Notebook · Lab guide · Python
07 Image patches & attention
Connect image representations with attention.
Notebook · Lab guide · Python
Recommended books
A selection of freely available books to support lectures, practical work and independent study.
Understanding Deep Learning
Simon J. D. Prince (2023). A conceptual introduction to neural networks and modern architectures, with diagrams and exercises.
Official book website · Free PDF available
Dive into Deep Learning
Aston Zhang, Zachary C. Lipton, Mu Li and Alexander J. Smola (2023). A practical companion with runnable examples that connect theory and implementation.
Read the book online
Deep Learning
Ian Goodfellow, Yoshua Bengio and Aaron Courville (2016). A reference for neural networks, optimisation, regularisation and probabilistic models.
Read the book online
Mathematics for Machine Learning
Marc Peter Deisenroth, A. Aldo Faisal and Cheng Soon Ong (2020). Mathematical preparation in linear algebra, calculus, probability and optimisation.
Official book website · Free PDF available
Teaching & student support
Learning through practice
The teaching materials connect foundational concepts with practical experiments. Use the examples to inspect model behaviour, test assumptions and build reproducible workflows.
Biomedical engineering labs
Mechanics and Electronics practicals connect circuit theory with biomedical applications through operational amplifiers, SPICE simulation and signal filtering. An electronic stethoscope project brings these topics together.
Project supervision
Projects in robotics, AI and bioengineering emphasise clear research questions, experimental design, reproducible evaluation and communication of results.
Help & course access
Current lecture slides, assessment instructions, deadlines and submissions are provided through the official Imperial module platform. For course materials or GitHub access, contact the teaching team with your module code and the resource title.