Week 1: Introduction to Deep Learning

Course Generated Slides: Linear Regression | Neural Networks

1. Introduction and Context

  • Brief history of machine learning
  • Types of machine learning
    • Supervised learning
    • Unsupervised learning
    • Reinforcement learning
  • Why deep learning?
  • Key applications and successes
  • Evolution of deep learning frameworks

2. Basic Neural Network Concepts

  • From logistic regression to single neuron
  • Basic architecture of neural networks
    • Layers
    • Weights and biases
    • Forward propagation intuition
  • Common activation functions
    • Sigmoid
    • ReLU
  • Simple loss functions introduction

3. Deep Learning Frameworks

  • PyTorch vs TensorFlow comparison
    • Philosophy and approach differences
    • Dynamic vs Static graphs
    • Eager execution
    • Development workflow differences
  • Basic tensor operations overview
  • Simple example concepts in both frameworks
  • PyTorch's role in research
  • TensorFlow's role in production

Required Reading

  • Deep Learning Fundamentals
  • Evolution of Neural Networks
  • Deep Learning with PyTorch - Official PyTorch textbook covering deep learning fundamentals and implementation

Video Resources

  • Neural Networks - 3Blue1Brown's visual introduction to neural networks and deep learning concepts

Learning Objectives

  • Understand the fundamental concepts of deep learning
  • Differentiate between types of machine learning
  • Grasp basic neural network architecture
  • Understand the key differences between PyTorch and TensorFlow

Additional Resources

Week 2: Neural Networks & Backpropagation →