Module 14: Recurrent Neural Networks

Modeling sequences — text, time series, and any data where order matters. This module covers recurrent architectures and their training dynamics, with applications to sentiment analysis and character-level text generation.

What You’ll Learn¶

• Why sequential data breaks feedforward assumptions

• The recurrent computation and backpropagation through time

• Vanishing/exploding gradients and the LSTM solution

• Sentiment classification with RNNs

• Character-level language modeling and text generation

Lecture Materials¶

• 📊 Lecture Slides (PDF)

• 📓 Chapter notebook: Modeling Sequential Data Using Recurrent Neural Networks

Prerequisites¶

• Modules 10–11

Reference¶

Raschka & Mirjalili, Machine Learning with PyTorch and Scikit-Learn, Chapter 15.