Python Status: Pending Migration

📖 Neural Networks¶

  • 🧠 Introduction to Neural Networks
    • 🔑 What is a Neural Network?
    • 🎯 Why Neural Networks? (vs. Traditional ML)
    • 🌍 Real-world Applications
  • 🔧 Setup Problem and Dataset
    • 📝 Define a Simple Classification Problem
    • 📊 Visualize the Dataset
    • 💡 Define Model Input/Output
  • 🛠️ Building Blocks of Neural Networks
    • 🔲 Neurons: Inputs, Weights, Biases, Activation Functions
    • 🔗 Layers: Input, Hidden, Output
    • 🔄 Forward Propagation (math and code)
  • ⚙️ Training Neural Networks
    • 📝 Loss Functions (e.g., MSE, Cross-Entropy)
    • 🔁 Backpropagation (Chain Rule, Gradients)
    • 🚀 Gradient Descent and Variants (SGD, Adam)
  • 🔬 Neural Network Architectures
    • ⚡ Feedforward Neural Networks (MLP)
    • 🔍 Convolutional Neural Networks (CNN) – High level
    • 🔄 Recurrent Neural Networks (RNN) – High level
    • ❓ When to use what?
  • 🛠️ Improving Neural Networks
    • ⚖️ Overfitting and Underfitting
    • 🔧 Regularization (Dropout, L2)
    • 📈 Batch Normalization
    • ⚙️ Hyperparameter Tuning (Learning Rate, Batch Size, Layers)
  • 📚 Applications and Case Studies
    • 🔢 Small Handwritten Digit Classifier (e.g., MNIST 1000 samples subset)
    • 📈 Tiny Time Series Predictor
  • 🔚 Closing Notes
    • ⚠️ Common Pitfalls
    • 🎯 Best Practices
    • ⚡ Scaling Challenges
    • 🚀 Further Topics
    • 🔮 What Next

🧠 Introduction to Neural Networks¶

🔑 What is a Neural Network?¶

🎯 Why Neural Networks? (vs. Traditional ML)¶

🌍 Real-world Applications¶

Back to the top

🔧 Setup Problem and Dataset¶

📝 Define a Simple Classification Problem¶

📊 Visualize the Dataset¶

💡 Define Model Input/Output¶

Back to the top

🛠️ Building Blocks of Neural Networks¶

🔲 Neurons: Inputs, Weights, Biases, Activation Functions¶

🔗 Layers: Input, Hidden, Output¶

🔄 Forward Propagation (math and code)¶

Back to the top

⚙️ Training Neural Networks¶

📝 Loss Functions (e.g., MSE, Cross-Entropy)¶

🔁 Backpropagation (Chain Rule, Gradients)¶

🚀 Gradient Descent and Variants (SGD, Adam)¶

Back to the top

🔬 Neural Network Architectures¶

⚡ Feedforward Neural Networks (MLP)¶

🔍 Convolutional Neural Networks (CNN) – High level¶

🔄 Recurrent Neural Networks (RNN) – High level¶

❓ When to use what?¶

Back to the top

🛠️ Improving Neural Networks¶

⚖️ Overfitting and Underfitting¶

🔧 Regularization (Dropout, L2)¶

📈 Batch Normalization¶

⚙️ Hyperparameter Tuning (Learning Rate, Batch Size, Layers)¶

Back to the top

📚 Applications and Case Studies¶

🔢 Small Handwritten Digit Classifier (e.g., MNIST 1000 samples subset)¶

📈 Tiny Time Series Predictor¶

Back to the top

🔚 Closing Notes¶

⚠️ Common Pitfalls¶

🎯 Best Practices¶

⚡ Scaling Challenges¶

🚀 Further Topics¶

🔮 What Next¶

Back to the top