← Back to curriculum

Module 4 — Deep learning architectures

Welcome to Module 4

How Module 4 extends Module 3, architecture overview, and what to install before the sentiment project.

~25 min read + exercises

Welcome to Module 4 — deep learning architectures

Before we begin

Module 3 gave you a fully connected network on MNIST. Real problems have structure:

Images have local patterns (edges, textures). Language has order and meaning beyond bag-of-words.

Module 4 introduces the architectures that dominated deep learning before transformers — and whose ideas still live inside modern models:

  • CNNs for images
  • RNNs for sequences
  • LSTM / GRU for longer memory
  • Embeddings for words (critical for GenAI)

Figure

Module 4 at a glance

Module 4 — deep learning architectures1WelcomeModule 42CNNimages3RNNsequences4LSTMmemory5Embedvectors6Quizcheck7Projectsentiment
Four architecture lessons, quiz, then sentiment analysis with a trend dashboard.

What Module 4 covers

TopicWhat you will understand
CNNConv filters, pooling, why spatial structure matters
RNNHidden state over time, sequences
LSTM / GRUGates, long-range context
EmbeddingsWords as vectors; pre-trained vs learned

Before you start

Required: Module 3 project or comfort with PyTorch training loops.

Install before the project:

  • pip install torch pandas matplotlib scikit-learn

Lessons 1–5 are reading. Lesson 7 is the coding project.


Ready?

Lesson 1 — Convolutional neural networks