Course Syllabus

Welcome to this course on AI models for NLP and language understanding.

In your generative AI journey, this course is a stepping stone toward learning about language understanding. It is an ideal course to learn various aspects of natural language processing (NLP) and AI model development.

Let’s get into the details.

In this course, you will learn about various language and neural network models such as n-grams, word2vec, and sequence-to-sequence. The course focuses mainly on architecture with one hidden layer. Further, you will learn about metrics to evaluate the quality of the generated text.

You will get hands-on opportunities through labs to build and train a simple language model, integrate the word2vec model, and develop a sequence-to-sequence model.

After completing this course, you will be able to:

Explain how to use one-hot encoding, bag-of-words, embedding, and embedding bags to convert words to features.
Describe how neural networks are used for document categorization prediction.
Describe the process of training and optimizing neural networks for document categorization.
Describe the applications of N-Gram language models in natural language processing.
Explain the types and features of word2Vec embedding models.
Describe how to use metrics for evaluating the quality of the generated text.
Describe the purpose of sequence-to-sequence models in natural language processing and sequence transformation tasks.
Implement document classification using torchtext and PyTorch.
Build and train a simple language model with a neural network.
Integrate pre-trained embedding models, such as word2Vec, for text analysis or classification.
Develop a sequence-to-sequence model in PyTorch for sequence transformation tasks.

Who should take this course?

This course is suitable for those interested in AI engineering, including creating, optimizing, training, and deploying AI models. It is specifically designed for those who want to learn about generative AI and neural network models.

Recommended background

As this is an intermediate-level course, it assumes that you have a basic knowledge of Python and PyTorch and a familiarity with machine learning and neural network concepts.

Course content

This course is approximately eight hours long and is divided into two modules. You can complete one module a week or at a pace that suits you.

Week 1 - Module 1: Fundamentals of Language Understanding

This module is divided into two lessons. The first lesson, Language Understanding with Neural Networks, focuses on concepts such as one-hot encoding, bag-of-words, embeddings, and embedding bags. You will also gain knowledge of neural networks, their architecture and hyperparameters, cross-entropy loss, and optimization.

In the second lesson of this module, N-Gram Model, you will delve into the concept of language modeling with n-grams and how they are used as neural networks with PyTorch. The module also includes hands-on labs on document classification with PyTorch and building a simple language model with a neural network.

Week 2 - Module 2: Word2Vec and Sequence-to-Sequence Models

In Module 2, you will learn about the word2vec embedding model and its types. You will also be introduced to sequence-to-sequence models and how they employ recurrent neural networks (RNNs) to process variable-length input sequences and generate variable-length output sequences. You will gain insights about encoder-decoder RNN models, their architecture, and how to build them using PyTorch. The module will give you knowledge about evaluating the quality of text using perplexity, precision, and recall in text generation. A reading has also been included to advance your learning on NLP-specific metrics.

You will integrate pre-trained embedding models for text analysis or classification and develop a sequence-to-sequence model for sequence transformation tasks.

The module includes a cheat sheet with quick reference content, such as code snippets. The summaries in each lesson will help you revisit the concepts you learned through videos. A glossary will help you review the technical terms used in the course. The modules conclude with a final graded quiz.

Please note: This course does not cover data acquisition techniques such as web crawling, initial data cleaning procedures, or the use of regular expressions. When you practice the lab exercises, you may want to ensure that you have well-prepared data by removing unwanted characters, symbols, etc.

Learning resources

The course offers a variety of learning assets: Videos, readings, hands-on labs, a cheat sheet, a glossary, and quizzes.

The videos and readings present the instruction, supported by labs that provide hands-on learning experiences.

The cheat sheet provides quick reference material, such as code snippets.

The glossary provides a reference list for all the technical terms used in the course, along with their definitions.

Practice quizzes at the end of each lesson test your understanding of what you learned, and the graded quizzes will assess your conceptual understanding of the course.

We wish you good luck completing the course and getting the most out of it!

Gen AI Foundational Models for NLP & Language Understanding

Language

Topic

Industries

Enrollment Count

Skills You Will Learn

Offered By

Estimated Effort

Platform

Last Update