Deep Learning with Python: Sequence Models and Transformers
1h 26mIntermediate2025-04-29
Authors
Frederick Nwanganga
Information Technology Professional and Teacher
Course details
This course focuses on sequence models and transformers, essential for tasks involving sequential data such as time series analysis and natural language processing (NLP). Emphasizing practical applications, the course includes hands-on coding exercises. Instructor Fred Nwanganga explains what sequence data is, common sequence data problems, recurrent neural networks and its variants, transformers, and how to solve several types of sequence data problems using pre-trained transformer models in Python.
Learning objectives
Understand what sequence data is and common use cases of sequence data.
Be able to work with the architecture of recurrent neural networks (RNN) and how to build an RNN in Python.
Understand the architecture of long short-term memory (LSTM) networks, gated recurrent unit (GRU) networks and transformers.
Know how to train and fine-tune pre-trained transformers in Python to solve a wide variety of problems.
Learning objectives
Understand what sequence data is and common use cases of sequence data.
Be able to work with the architecture of recurrent neural networks (RNN) and how to build an RNN in Python.
Understand the architecture of long short-term memory (LSTM) networks, gated recurrent unit (GRU) networks and transformers.
Know how to train and fine-tune pre-trained transformers in Python to solve a wide variety of problems.
Skills covered
Neural Networks and Deep LearningPythonArtificial Intelligence (AI)Programming LanguagesOpen SourceSoftware DevelopmentOne-Off
Concepts
0. Introduction
- 01 - Getting started with sequence models and transformers
- 02 - What you should know
- 03 - Using the exercise files
1. Recurrent Neural Networks
- 04 - What is sequence data
- 05 - Common uses of sequence models
- 06 - Recurrent neural networks (RNNs)
- 07 - Building a simple RNN with Keras
2. Advanced RNN Architectures
- 08 - The vanishing and exploding gradient problems
- 09 - Solutions to the vanishing and exploding gradient problems
- 10 - Long short-term memory networks (LSTMs)
- 11 - Gated recurrent units (GRUs)
- 12 - Choosing between GRUs and LSTMs
3. Transformer Models
- 13 - Attention and its importance in sequence models
- 14 - Architecture of the transformer model
- 15 - What is transfer learning
- 16 - The Hugging Face hub
- 17 - Choosing the right model from the Hugging Face hub
4. Using Pre-trained Transformer Models
- 18 - Named entity recognition with pretrained models in Python
- 19 - Part-of-speech tagging with pretrained models in Python
- 20 - Sentiment analysis with pretrained models in Python
- 21 - Topic classification with pretrained models in Python
- 22 - Text summarization with pretrained models in Python
- 23 - Question answering with pretrained models in Python
Conclusion
- 24 - Continuing on with deep learning