All Topics
🧠Deep Learning
🧠

Neural Network Fundamentals

Understand the building blocks of deep learning from perceptrons to multi-layer networks

🌱

Beginner

Beginner

Build intuition for neural networks

What to Learn

  • Perceptron and activation functions
  • Forward propagation step by step
  • Backpropagation intuition
  • Loss functions (MSE, Cross-entropy)
  • Training with mini-batch gradient descent

Resources

  • 📚3Blue1Brown: Neural Networks
  • 📚Michael Nielsen: Neural Networks and Deep Learning
  • 📚PyTorch 60-minute blitz
🌿

Intermediate

Intermediate

Deep dive into architectures

What to Learn

  • Activation functions comparison (ReLU, GELU, Swish)
  • Batch normalization and layer normalization
  • Dropout and regularization techniques
  • Weight initialization strategies
  • Residual connections and skip connections

Resources

  • 📚Deep Learning book Part II
  • 📚Stanford CS231n lecture notes
  • 📚Implementing networks from scratch
🌳

Advanced

Advanced

Cutting-edge neural architectures

What to Learn

  • Neural architecture search (NAS)
  • Dynamic neural networks
  • Sparsity and efficient architectures
  • Knowledge distillation
  • Multi-task and meta-learning

Resources

  • 📚NAS survey papers
  • 📚EfficientNet and MobileNet papers
  • 📚Neural network compression research