Deep Learning for NLP with Python

Interactive Online Course

• Tentative Start Date: Oct. 10th  (if the minimum enrollment limit of 10 is met)
• Saturdays, 10:00 am – 12:00 pm EDT
• Length: 10 weeks (20 hrs)

Important Notes: 

• A “Certificate of Completion” will be awarded to you, if you pass the final exam.
• The full price of the course is $130. If you register before Oct. 5th, you can register with $30 off (i.e. discounted price is $100).
• The lectures are in either in Farsi or English, but course material is in English.
• The course is associated with an R&D projects with specific benefits for students.

Course Description

If you know the basic underlying of machine learning and you would like to learn how to run an AI project on time-series data, this is the right place for you to learn the state-of-the-art sequence models. More specifically, we discuss the natural language processing (NLP) in which data is a sequence of words/letters.

In the first part, we learn the basics of NLP and recurrent neural networks (RNNs) which are widely used in sequence modeling for time-series data. Besides a multi-label classification task in Lab 1 with Python, we experience a deep learning implementation for sequence tagging in Lab 2 with PyTorch DL framework. The second part also discusses attention mechanisms and Transformers, which are also state-of-the-art sequence modeling techniques. We learn how to use pre-trained models in a transfer learning fashion for new tasks with small supervised data.

Avoiding from the complex mathematics, this course comprehensibly presents the underlying concepts of the deep learning models for time-series data (RNNs) and their applications. Moreover, we will review attention models. The concepts are supported by Lab session(s) by introducing popular python libraries and implementing some samples.

Course Outline

Part 1

1. Introduction (Definitions, Applications, Tasks, Approaches)
2. Basics of Linguistics (NLP Pyramid, Vectorizations: BoW, TF-IDF, word2vec)
3. Lab 1. Automatic Tagging in Python
4. Recurrent Neural Networks (ML Components, LSTM, GRU)
5. Lab 2. Named Entity Recognition in PyTorch

Part 2

1. Attention mechanisms & Transformers
2. BERT
3. Lab 3. Spam classification with BERT in PyTorch
4. Chatbots & Question/Answering
5. Lab 4. Q/A with BERT in PyTorch

Prerequisites

• It is highly suggested to complete the Introduction to AI & ML and Unsupervised Learning courses in advance.
• Basic Python programming is needed. For the lab session, we use Google Colab. So, you don’t need to install anything in your machine. The DL programs employs PyTorch framework.

Resources

• Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT press.

The AI & ML Series

DL for NLP with Python is the third course in the AI & ML series. List of courses in the AI & ML boot camp is as follows:

1. Introduction to AI & ML
2. Unsupervised Learning
3. DL for NLP with Python
4. Reinforcement Learning
5. Convolutional Neural Networks