Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

Natural Language Processing with Deep Learning in Python

Name: Natural Language Processing with Deep Learning in Python
Rating: 4.7 (8587 reviews)

Complete guide on deriving and implementing word2vec, GloVe, word embeddings, and sentiment analysis with recursive nets

Created byLazy Programmer Inc., Lazy Programmer Team

Last updated 2/2026

English

What you'll learn

Understand and implement word2vec
Understand the CBOW method in word2vec
Understand the skip-gram method in word2vec
Understand the negative sampling optimization in word2vec
Understand and implement GloVe using gradient descent and alternating least squares
Use recurrent neural networks for parts-of-speech tagging
Use recurrent neural networks for named entity recognition
Understand and implement recursive neural networks for sentiment analysis
Understand and implement recursive neural tensor networks for sentiment analysis
Use Gensim to obtain pretrained word vectors and compute similarities and analogies
Understand important foundations for OpenAI ChatGPT, GPT-4, DALL-E, Midjourney, and Stable Diffusion

Course content

14 sections • 96 lectures • 12h 2m total length

Introduction, Outline, and Review5:35
Explore how deep learning boosted natural language processing, covering word embeddings like word2vec and glove, and neural architectures from rnn to recursive models for text tasks.
How to Succeed in this Course3:04
Where to get the code / data for this course9:17
Preprocessed Wikipedia Data3:03
How to Open Files for Windows Users2:18

What are vectors?7:56
What is a word analogy?7:58
Explore how word analogies arise from word embeddings and vectors, and learn to compute analogies using vector arithmetic and cosine distance.
Trying to find and assess word vectors using TF-IDF and t-SNE7:42
Explore how tf-idf derived word vectors are reduced with t-SNE and plotted as a scatterplot to test semantic analogies, highlighting the limitations of tf-idf for word relationships.
Pretrained word vectors from GloVe11:05
Pretrained word vectors from word2vec6:31
Text Classification with word vectors4:24
Text Classification in Code6:14
Using pretrained vectors later in the course3:32
Explore how word embeddings initialize language models using pretrained vectors from word2vec and glove. Experiment with freezing embeddings or keeping them trainable to see effects on rnn performance.
Suggestion Box3:10

Review Section Intro3:13
Bigrams and Language Models14:47
Bigrams in Code14:19
Neural Bigram Model7:56
Extend a neural bigram model with logistic regression using one-hot word encoding, train with gradient descent to minimize cross-entropy, and compare weight matrices with the probability matrix.
Neural Bigram Model in Code6:48
Neural Network Bigram Model9:13
Neural Network Bigram Model in Code3:31
Improving Efficiency14:35
Improving Efficiency in Code4:52
Review Section Summary3:26

Return of the Bigram3:07
Examine how a bigram neural network models the next word as a language model and builds word embeddings with two V-by-V matrices.
CBOW7:39
Skip-Gram4:00
Hierarchical Softmax8:22
Negative Sampling14:11
Explore negative sampling as a scalable alternative to softmax in natural language processing, using binary cross entropy, sigmoid outputs, and context word sampling within skip gram and cbow frameworks.
Negative Sampling - Important Details5:09
Why do I have 2 word embedding matrices and what do I do with them?2:16
Word2Vec implementation tricks4:49
Word2Vec implementation outline4:09
Word2Vec in Code with Numpy10:47
Tensorflow or Theano - Your Choice!4:09
Word2Vec Tensorflow Implementation Details3:58
Word2Vec Tensorflow in Code4:06
Alternative to Wikipedia Data: Brown Corpus6:03

GloVe Section Introduction2:19
Explore GloVe, global vectors for word representation, and learn how matrix factorization from recommender systems underpins word vectors for NLP, offering simpler training with fewer hyperparameters.
Matrix Factorization for Recommender Systems - Basic Concepts21:08
Matrix Factorization Training8:11
Expanding the Matrix Factorization Model9:23
Regularization for Matrix Factorization6:18
Apply regularization to a matrix factorization model using the Frobenius norm, deriving update rules for W, U, and bias terms to prevent overfitting.
GloVe - Global Vectors for Word Representation4:12
Recap of ways to train GloVe2:31
GloVe in Code - Numpy Gradient Descent16:48
GloVe in Code - Alternating Least Squares4:42
GloVe in Tensorflow with Gradient Descent7:03
Visualizing country analogies with t-SNE4:24
Hyperparameter Challenge2:19
Try new word analogies beyond countries and cities to test your natural language processing model, and tune hyperparameters like learning rate, momentum, embedding dimensionality, and vocabulary size.
Training GloVe with SVD (Singular Value Decomposition)10:38

Parts-of-Speech (POS) Tagging5:00
How can neural networks be used to solve POS tagging?4:08
Explore how logistic regression, hidden Markov models, and recurrent neural networks tackle parts of speech tagging, highlighting context, long term dependencies, and the role of LSTM/GRU units.
Parts-of-Speech Tagging Baseline15:18
Parts-of-Speech Tagging Recurrent Neural Network in Theano13:05
Explore how a recurrent neural network in Theano solves the parts-of-speech tagging problem, using word embeddings, softmax outputs, and F1 score evaluation.
Parts-of-Speech Tagging Recurrent Neural Network in Tensorflow12:17
How does an HMM solve POS tagging?7:57
Parts-of-Speech Tagging Hidden Markov Model (HMM)5:58
Named Entity Recognition (NER)3:01
Comparing NER and POS tagging2:01
Named Entity Recognition Baseline5:54
Named Entity Recognition RNN in Theano2:19
Develop a named entity recognition model with an RNN in Theano for natural language processing using Python and deep learning, and evaluate performance with train and test data.
Named Entity Recognition RNN in Tensorflow2:13
Hyperparameter Challenge II2:13

Recursive Neural Networks Section Introduction7:14
Sentences as Trees5:29
Represent sentences as trees using parts of speech to form noun phrases and verb phrases, then apply sentiment analysis and negation handling, paving the way toward recursive neural networks.
Data Description for Recursive Neural Networks6:52
What are Recursive Neural Networks / Tree Neural Networks (TNNs)?5:41
Explore the architecture of recursive neural networks for binary and multi-child trees, detailing how shared weights connect to parse tree nodes, compute hidden states, and produce outputs with softmax.
Building a TNN with Recursion4:47
Trees to Sequences6:38
Transform parse trees into sequences to convert recursive neural networks into recurrent neural networks, using three arrays (parents, relations, and words) and post-order traversal to build a scalable tree-to-sequence pipeline.
Recursive Neural Tensor Networks6:22
RNTN in Tensorflow (Tips)12:19
RNTN in Tensorflow (Code)11:19
Recursive Neural Network in TensorFlow with Recursion4:12
Explore a practical recursive neural network implemented in TensorFlow, using post-order traversal, tree-based graphs, and a custom training loop with Savir to save and load weights.

(Review) Theano Basics7:47
Discover Theano basics, including symbolic variables and tensors of various shapes, and build functions. Learn automatic gradients with shared variables and a simple training loop to minimize a cost.
(Review) Theano Neural Network in Code9:17
(Review) Tensorflow Basics7:27
Explore TensorFlow basics, including placeholders, variables, sessions, and simple matrix multiplication, then minimize a cost function with gradient descent using a learning rate of 0.3.
(Review) Tensorflow Neural Network in Code9:43
Build a TensorFlow neural network with a second hidden layer of 100 units, configure placeholders and variables, and train using momentum-based optimizers while monitoring cost and potential overfitting.

Requirements

Install Numpy, Matplotlib, Sci-Kit Learn, and Theano or TensorFlow (should be extremely easy by now)
Understand backpropagation and gradient descent, be able to derive and code the equations on your own
Code a recurrent neural network from basic primitives in Theano (or Tensorflow), especially the scan function
Code a feedforward neural network in Theano (or Tensorflow)
Helpful to have experience with tree algorithms

Description

Ever wondered how AI technologies like OpenAI ChatGPT, GPT-4, DALL-E, Midjourney, and Stable Diffusion really work? In this course, you will learn the foundations of these groundbreaking applications.

In this course we are going to look at NLP (natural language processing) with deep learning.

Previously, you learned about some of the basics, like how many NLP problems are just regular machine learning and data science problems in disguise, and simple, practical methods like bag-of-words and term-document matrices.

These allowed us to do some pretty cool things, like detect spam emails, write poetry, spin articles, and group together similar words.

In this course I’m going to show you how to do even more awesome things. We’ll learn not just 1, but 4 new architectures in this course.

First up is word2vec.

In this course, I’m going to show you exactly how word2vec works, from theory to implementation, and you’ll see that it’s merely the application of skills you already know.

Word2vec is interesting because it magically maps words to a vector space where you can find analogies, like:

king - man = queen - woman
France - Paris = England - London
December - Novemeber = July - June

For those beginners who find algorithms tough and just want to use a library, we will demonstrate the use of the Gensim library to obtain pre-trained word vectors, compute similarities and analogies, and apply those word vectors to build text classifiers.

We are also going to look at the GloVe method, which also finds word vectors, but uses a technique called matrix factorization, which is a popular algorithm for recommender systems.

Amazingly, the word vectors produced by GLoVe are just as good as the ones produced by word2vec, and it’s way easier to train.

We will also look at some classical NLP problems, like parts-of-speech tagging and named entity recognition, and use recurrent neural networks to solve them. You’ll see that just about any problem can be solved using neural networks, but you’ll also learn the dangers of having too much complexity.

Lastly, you’ll learn about recursive neural networks, which finally help us solve the problem of negation in sentiment analysis. Recursive neural networks exploit the fact that sentences have a tree structure, and we can finally get away from naively using bag-of-words.

All of the materials required for this course can be downloaded and installed for FREE. We will do most of our work in Numpy, Matplotlib, and Theano. 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!

"If you can't implement it, you don't understand it"

Or as the great physicist Richard Feynman said: "What I cannot create, I do not understand".
My courses are the ONLY courses where you will learn how to implement machine learning algorithms from scratch
Other courses will teach you how to plug in your data into a library, but do you really need help with 3 lines of code?
After doing the same thing with 10 datasets, you realize you didn't learn 10 things. You learned 1 thing, and just repeated the same 3 lines of code 10 times...

Suggested Prerequisites:

calculus (taking derivatives)
matrix addition, multiplication
probability (conditional and joint distributions)
Python coding: if/else, loops, lists, dicts, sets
Numpy coding: matrix and vector operations, loading a CSV file
neural networks and backpropagation, be able to derive and code gradient descent algorithms on your own
Can write a feedforward neural network in Theano or TensorFlow
Can write a recurrent neural network / LSTM / GRU in Theano or TensorFlow from basic primitives, especially the scan function
Helpful to have experience with tree algorithms

WHAT ORDER SHOULD I TAKE YOUR COURSES IN?:

Check out the lecture "Machine Learning and AI Prerequisite Roadmap" (available in the FAQ of any of my courses, including the free Numpy course)

UNIQUE FEATURES

Every line of code explained in detail - email me any time if you disagree
No wasted time "typing" on the keyboard like other courses - let's be honest, nobody can really write code worth learning about in just 20 minutes from scratch
Not afraid of university-level math - get important details about algorithms that other courses leave out

Who this course is for:

Students and professionals who want to create word vector representations for various NLP tasks
Students and professionals who are interested in state-of-the-art neural network architectures like recursive neural networks
SHOULD NOT: Anyone who is not comfortable with the prerequisites.

Natural Language Processing with Deep Learning in Python

What you'll learn

Explore related topics

Course content

Outline, Review, and Logistical Things5 lectures • 23min

Beginner's Corner: Working with Word Vectors9 lectures • 59min

Review of Language Modeling and Neural Networks10 lectures • 1hr 23min

Word Embeddings and Word2Vec14 lectures • 1hr 23min

Word Embeddings using GloVe13 lectures • 1hr 40min

Unifying Word2Vec and GloVe2 lectures • 19min

Using Neural Networks to Solve NLP Problems13 lectures • 1hr 21min

Recursive Neural Networks (Tree Neural Networks)10 lectures • 1hr 11min

Theano and Tensorflow Basics Review4 lectures • 34min

Appendix / FAQ Finale1 lecture • 4min

Requirements

Description

Who this course is for: