Data Science & MLAdvanced
Deep Learning & Neural Networks
A comprehensive three-day intensive covering the architecture and training of deep neural networks. You will build CNNs for image classification, work with sequence models, and apply transformer-based models via Hugging Face. Suitable for those with solid ML foundations who are ready to go deeper. The extended format allows proper coverage of the mathematical foundations and hands-on implementation time.
Tools & Technologies
PythonTensorFlowKerasPyTorchHugging Face
Course Curriculum
1
Neural Network Foundations
- Perceptrons and activation functions
- Backpropagation and gradient descent
- Optimisers: Adam, SGD, learning rate schedules
2
Convolutional Networks
- CNN architecture and filter intuition
- Image classification in practice
- Transfer learning with ResNet and EfficientNet
3
Sequence Models & Attention
- RNNs, LSTMs, and their limitations
- Attention mechanisms — the intuition
- Introduction to the Transformer architecture
4
Modern Practice
- Hugging Face — loading and fine-tuning pre-trained models
- Training callbacks, early stopping, and regularisation
- Practical considerations: compute, batch size, mixed precision
What's Included
Live instructor-led session
Small cohort
Course materials pack (slides, code, datasets)
Certificate of completion
14-day email support
£2,980Early bird
£1,995Save £985
per person
21 hours (3 days)
Next: Tue, 16 Jun 2026
5 seats remaining
Advanced level
5/10 seats filled
Completion certificate included