OVERVIEW 📋
Welcome to the University of Manchester FSE Deep Learning workshop! This course provides a hands-on introduction to deep learning using PyTorch.
This hands-on workshop introduces the fundamentals of deep learning using PyTorch. Participants will learn by building real models and solving practical tasks. The workshop is designed for beginners and covers essential concepts.
WHAT YOU'LL LEARN
- Core PyTorch concepts (tensors, autograd, GPU usage)
- Building and training neural networks
- Understanding the architecture of neural networks
- Physics-informed neural networks (PINNs)
- Implementing CNNs for vision tasks
- Applying transfer learning with pre-trained models
- Working with real-world datasets
- Designing classification and regression models
WORKSHOP SESSIONS 🧠
WORKSHOP CURRICULUM
| Session | Topic | Duration | Materials |
|---|---|---|---|
| 1 | PyTorch Basics & Tensors | ~1 hr | Notebook | Slides |
| 2 | Artificial Neural Networks (ANNs) | ~1.5 hr | Notebook | Slides |
| 3 | Model Training & Optimization | ~0.5 hr | Notebook | Slides |
| 3B | Physics-Informed Neural Networks (PINNS) | ~1 hr | Notebook | Slides |
| 4 | Convolutional Neural Networks (CNNs) | ~2 hr | Notebook | Slides |
| 5 | Transfer Learning & U-Net | ~2 hr | Notebook | Slides |
LEARNING OUTCOMES 🎯
BY THE END, YOU'LL BE ABLE TO:
- Build and train models in PyTorch
- Apply CNNs to classification & segmentation
- Fine-tune pre-trained models on new tasks
- Use PyTorch effectively for real-world datasets
GETTING STARTED 🛠️
RECOMMENDED PLATFORM: GOOGLE COLAB
Colab provides a free, GPU-enabled environment—ideal for this workshop.
WHAT YOU NEED
- A Google account
- Reliable internet connection
PREREQUISITES ✅
- Basic Python skills
- Some knowledge of basic machine learning concepts
- Familiarity with linear algebra/calculus (optional)
- No PyTorch experience required!