Overview
This section covers key methods for evaluating predictive models and introduces deep learning concepts.
Model Evaluation
- Accuracy, Precision, Recall, F1-Score
- Confusion Matrix and ROC Curves
- Cross-Validation and Train/Test Splits
- Overfitting vs. Underfitting
Deep Learning
- Introduction to Neural Networks
- Activation Functions (ReLU, Sigmoid, Tanh)
- Backpropagation and Gradient Descent
- Common Architectures: Feedforward, CNNs, RNNs
- Practical Considerations: Learning Rate, Regularization, Dropout