Deep Learning: Advanced NLP and RNNs

Natural Language Processing with Sequence-to-sequence (seq2seq), Attention, CNNs, RNNs, and Memory Networks!

Register for this Course

$30.00 $200.00 USD 85% OFF!

Login or signup to register for this course

Have a coupon? Click here.

Course Data

Lectures: 57
Length: 07h 21m
Skill Level: All Levels
Languages: English
Includes: Lifetime access, 30-day money back guarantee

Course Description

It’s hard to believe it's been been over a year since I released my first course on Deep Learning with NLP (natural language processing).

A lot of cool stuff has happened since then, and I've been deep in the trenches learning, researching, and accumulating the best and most useful ideas to bring them back to you.

So what is this course all about, and how have things changed since then?

In previous courses, you learned about some of the fundamental building blocks of Deep NLP. We looked at RNNs (recurrent neural networks), CNNs (convolutional neural networks), and word embedding algorithms such as word2vec and GloVe.

This course takes you to a higher systems level of thinking.

Since you know how these things work, it’s time to build systems using these components.

At the end of this course, you'll be able to build applications for problems like:

  • text classification (examples are sentiment analysis and spam detection)
  • neural machine translation
  • question answering

In the bonus section, we'll be looking at speech recognition using Deep Learning.

We'll take a brief look chatbots and as you’ll learn in this course, this problem is actually no different from machine translation and question answering.

To solve these problems, we’re going to look at some advanced Deep NLP techniques, such as:

  • bidirectional RNNs
  • seq2seq (sequence-to-sequence)
  • attention
  • memory networks

All of the materials of this course can be downloaded and installed for FREE. We will do most of our work in Python libraries such as Keras, Numpy, Tensorflow, and Matpotlib to make things super easy and focus on the high-level concepts. I am always available to answer your questions and help you along your data science journey.

This course focuses on "how to build and understand", not just "how to use". Anyone can learn to use an API in 15 minutes after reading some documentation. It's not about "remembering facts", it's about "seeing for yourself" via experimentation. It will teach you how to visualize what's happening in the model internally. If you want more than just a superficial look at machine learning models, this course is for you.

See you in class!


All the code for this course can be downloaded from my github:

In the directory: nlp_class3

Make sure you always "git pull" so you have the latest version!


  • Decent Python coding skills
  • Understand RNNs, CNNs, and word embeddings
  • Know how to build, train, and evaluate a neural network in Keras

TIPS (for getting through the course):

  • Watch it at 2x.
  • Take handwritten notes. This will drastically increase your ability to retain the information.
  • Write down the equations. If you don't, I guarantee it will just look like gibberish.
  • Ask lots of questions on the discussion board. The more the better!
  • The best exercises will take you days or weeks to complete.
  • Write code yourself, don't just sit there and look at my code. This is not a philosophy course!


Welcome to Advanced NLP and RNNs

  1. Introduction (02:51) (FREE preview available)
  2. Outline (04:09)
  3. Where to get the code (04:45)
  4. How to succeed in this course (03:13)

Review of Recurrent Neural Networks, Convolutional Neural Networks, and Word Embeddings

  1. Review Section Introduction (04:24)
  2. What is a word embedding? (15:10)
  3. Using word embeddings (04:33)
  4. What is a CNN? (13:36)
  5. Where to get the data (05:06)
  6. CNN Code (part 1) (15:08)
  7. CNN Code (part 2) (06:14)
  8. What is an RNN? (13:11)
  9. GRUs and LSTMs (10:47)
  10. Different Types of RNN Tasks (12:27)
  11. A Simple RNN Experiment (06:29)
  12. RNN Code (03:25)
  13. Review Section Summary (04:49)

Bidirectional RNNs

  1. Bidirectional RNNs Motivation (08:31)
  2. Bidirectional RNN Experiment (05:09)
  3. Bidirectional RNN Code (02:33)
  4. Image Classification with Bidirectional RNNs (06:12)
  5. Image Classification Code (05:45)
  6. Bidirectional RNNs Section Summary (02:36)

Sequence-to-sequence models (Seq2Seq)

  1. Seq2Seq Theory (07:29)
  2. Seq2Seq Applications (03:27)
  3. Decoding in Detail and Teacher Forcing (06:47)
  4. Poetry Revisited (03:28)
  5. Poetry Revisited Code 1 (08:29)
  6. Poetry Revisited Code 2 (06:58)
  7. Seq2Seq in Code 1 (07:55)
  8. Seq2Seq in Code 2 (05:14)
  9. Seq2Seq Section Summary (03:04)


  1. Attention Section Introduction (02:28)
  2. Attention Theory (18:04)
  3. Teacher Forcing (02:09)
  4. Helpful Implementation Details (11:21)
  5. Attention Code 1 (09:48)
  6. Attention Code 2 (03:50)
  7. Visualizing Attention (02:26)
  8. Attention Section Summary (03:33)

Memory Networks

  1. Memory Networks Section Introduction (09:19)
  2. Memory Networks Theory (08:55)
  3. Memory Networks Code 1 (07:55)
  4. Memory Networks Code 2 (05:05)
  5. Memory Networks Code 3 (05:41)
  6. Memory Networks Section Summary (03:50)


  1. What is the Appendix? (02:48)
  2. Windows-Focused Environment Setup 2018 (20:21)
  3. How to How to install Numpy, Theano, Tensorflow, etc... (17:33)
  4. Is this for Beginners or Experts? Academic or Practical? Fast or slow-paced? (22:04)
  5. How to Succeed in this Course (Long Version) (10:25)
  6. How to Code by Yourself (part 1) (15:55)
  7. How to Code by Yourself (part 2) (09:23)
  8. What order should I take your courses in? (part 1) (11:19)
  9. What order should I take your courses in? (part 2) (16:07)
  10. Python 2 vs Python 3 (04:38)
  11. Where to get discount coupons and FREE deep learning material (02:21)


  • Speech Recognition (29 pages, 2 code files)