This comprehensive 4-week online course provides a practical introduction to natural language processing (NLP) using Python and HuggingFace Transformers. By the end of the course, you will have built real-world NLP applications and have a strong foundation in modern NLP techniques.


Week 1: Introduction to NLP Tasks

Learn about different NLP tasks like text classification, named entity recognition, question answering, translation, summarization and more. Learn how to implement these using HuggingFace.

Week 2: Transformers and Tokenization
Learn about transformer architecture. Understand the differences between encoder and decoder models. Learn about the role of tokenization for text preprocessing. Understand GPU resource utilization during model inference.

Week 3: Text Generation with Language Models
Learn techniques for automatically generating human-like text using language model APIs. Understand decoding methods like beam search, top-k sampling, and nucleus sampling

Week 4: Task-Specific Fine-tuning
Go beyond off-the-shelf models by fine-tuning transformer networks on your own data. Learn about transfer learning for domain-specific NLP tasks and few-shot learning techniques. Learn about GPU resource utilization during model training.


Who is this course for?


Working professionals looking to build industry specific applications


Professionals/Jobseekers looking to up-skill for career change


Students interested in creating academic projects


What will you get out of this course?


By the end of this comprehensive 4-week course, you will gain in-demand skills and practical experience in:

● Implementing NLP pipelines for text classification, named entity recognition, question answering, and other critical capabilities using Python and HuggingFace Transformers

● Understanding how modern transformer-based models like BERT work under the hood

● Generating human-like text using decoding strategies with language models

● Fine-tuning pre-trained models on custom datasets to achieve superior performance on domain-specific tasks

The course provides both breadth across fundamental NLP concepts and depth in implementing them hands-on in Python. You will walk away with production-ready skills and the ability to build NLP systems using modern machine learning approaches. The techniques covered serve as an on-ramp to more advanced NLP research and applications.


Meet Your Instructor

Dr. Santi Adavani is the Co-Founder of S2 Labs and the Founding Member and Head of AI at PostgresML. Prior to this role, Dr. Adavani was the Founder and CTO of RocketML where he led the development MLOps products for energy, precision medicine, financial services, and healthcare industries. His areas of expertise include natural language processing, computer vision, cloud computing and high-performance computing. Dr. Adavani has a Ph.D. in Computational Sciences and Engineering from the University of Pennsylvania and a Bachelors from Indian Institute of Technology Madras.


Course Schedule

● Course kicks off Sept 5th
● We meet live on Tuesdays 9-10 AM PST
● There will be weekly assignments, and we recommend that you team up with a fellow student for the best experience
● There will be office hours where we address your questions from the assignments

Frequently Asked Questions

What happens if I can’t make a live session?
All the sessions will be recorded in case you can't make it to the live sessions.


I work full-time, what is the expected time commitment?
This course runs for a total of 4 weeks. The sessions will be delivered one day a week for four consecutive weeks. The expected time commitment per week is 4-6 hours to complete assignments and go through reading material.

What’s the refund policy?
You can request a refund up until the day before the course begins, Sept. 5th, 2023.

What are the prerequisites for this course?
You will be using a mixture of both coding and no-code tools for this course. Basic knowledge of Python programming and a high-level familiarity with Jupyter or Google Colab will be useful.