TensorFlow: Working with NLP
41mIntermediate2022-02-02
Authors
Jonathan Fernandes
Consultant focusing on data science, AI, and big data
Course details
TensorFlow 2.0 is quickly becoming one of the most popular deep learning frameworks and a must-have skill in your artificial intelligence toolkit. Using a hands-on approach, Jonathan Fernandes covers the key aspects of working with transformers in natural language processing, all in TensorFlow. He goes over the basics of working with text data, and explores transfer learning, fine-tuning BERT, and understanding the transformer model architecture. He also includes challenge/solution sets and assessment questions to help you optimize retention of the material.
Skills covered
TensorFlowNeural Networks and Deep LearningNatural Language Processing (NLP)PythonGoogleArtificial Intelligence (AI)Open SourceDeep Dive (X:Y)
Concepts
Introduction
- Why TensorFlow
- What you should know
- What is TensorFlow
NLP and Transformers
- What is NLP
- Transformers for NLP
- Transformers, their use, and history
- Challenge - NLP model size
- Solution - NLP model size
BERT and Transfer Learning
- Bias in BERT and GPT
- How was BERT trained
- Transfer learning
Transformers and BERT
- Transformer - Architecture overview
- BERT model and tokenization
- Tokenizers
- Self-attention
- Multi-head attention and feedforward network
- Fine-tuning BERT
Conclusion
- Next steps