Title here
Summary here
Module · 6 lessons
NLP with Deep Learning
Process and understand human language with embeddings, sequence models, and transformers.
At a glance
Level
Advanced
Lessons
6 lessons
Time to complete
2–3 weeks
Cost
Free forever · no sign-up
Natural language processing teaches machines to understand text. This module covers tokenization, word embeddings, deep text classification, sequence models, and the transformer architecture behind modern language models — applied to a real tweet classification project.
Lessons in this module
1
Introduction to Natural Language Processing
Learn what natural language processing is, why text is hard for models, and the classic preprocessing pipeline using a real disaster tweets dataset
2
Text Vectorization and Word Embeddings
Turn raw tweets into numbers a neural network can learn from using the Keras TextVectorization and Embedding layers
3
Building Text Classification Models
Build your first neural text classifier in Keras with TextVectorization, an Embedding layer, GlobalAveragePooling1D, and Dense layers on real disaster tweets
4
Building Sequence Models for Text
Learn why word order matters and build an Embedding to Bidirectional LSTM classifier for disaster tweet detection with TensorFlow
5
Building Text Models with Transformers
Learn how self-attention powers transformers and build a small transformer block in Keras to classify disaster tweets
6
Guided Project: Classifying Disaster Tweets
Build an end-to-end deep learning pipeline that classifies disaster tweets, comparing a dense network, a BiLSTM, and a transformer
Achievement
Complete all 6 lessons to finish the NLP with Deep Learning module.