Students will learn to apply deep learning techniques for projects from different industries.

Contents

• Applied Math and Machine Learning Basics
• Neural Networks
• Convolutional Neural Networks
• Recurrent Neural Networks
• Generative Adversarial Networks
• Adversarial Machine Learning
• Future trends and challenges

Lectures

• Neural Network for Fashion MNIST

Jupyter Notebooks

• Python
  • Introduction to Python
  • Control Flow Tools
  • Data Structure
  • Modules
  • Input/Output
  • Error Exception
  • Classes
• PyTorch
  • Fashion-MNIST
  • Tensors
  • Datasets and Dataloaders
  • Transforms
  • Build Neural Network
  • Automatic Differentiation with torch.autograd
  • Optimizing Model Parameters
  • Save and Load Model
  • CNN for CIFAR10

Assessment

• Examination: 30%
• Coursework: 70%
  • Two lab tests ( 25%)
  • Two class tests (25%)
  • One project (20 %)

Recommended Books/Resources

• Introduction to Linear Algebra by Gilbert Strang, https://math.mit.edu/~gs/linearalgebra/
• The Python Tutorial, https://docs.python.org/3/tutorial/index.html
• Deep Learning by Ian Goodfellow and Yoshua Bengio and Aaron Courville, https://www.deeplearningbook.org
• Practical Deep Learning for Coders, https://course.fast.ai