Deep Learning: Recurrent Neural Networks in Python

GRU, LSTM, Time Series Forecasting, Stock Predictions, Natural Language Processing (NLP) using Artificial Intelligence

4.61 (4961 reviews)

Udemy

platform

English

language

Data Science

What you will learn

Apply RNNs to Time Series Forecasting (tackle the ubiquitous "Stock Prediction" problem)

Apply RNNs to Natural Language Processing (NLP) and Text Classification (Spam Detection)

Apply RNNs to Image Classification

Understand the simple recurrent unit (Elman unit), GRU, and LSTM (long short-term memory unit)

Write various recurrent networks in Tensorflow 2

Understand how to mitigate the vanishing gradient problem

Understand important foundations for OpenAI ChatGPT, GPT-4, DALL-E, Midjourney, and Stable Diffusion

Why take this course?

*** NOW IN TENSORFLOW 2 and PYTHON 3 ***

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.

Learn about one of the most powerful Deep Learning architectures yet!

The Recurrent Neural Network (RNN) has been used to obtain state-of-the-art results in sequence modeling.

This includes time series analysis, forecasting and natural language processing (NLP).

Learn about why RNNs beat old-school machine learning algorithms like Hidden Markov Models.

This course will teach you:

The basics of machine learning and neurons (just a review to get you warmed up!)
Neural networks for classification and regression (just a review to get you warmed up!)
How to model sequence data
How to model time series data
How to model text data for NLP (including preprocessing steps for text)
How to build an RNN using Tensorflow 2
How to use a GRU and LSTM in Tensorflow 2
How to do time series forecasting with Tensorflow 2
How to predict stock prices and stock returns with LSTMs in Tensorflow 2 (hint: it's not what you think!)
How to use Embeddings in Tensorflow 2 for NLP
How to build a Text Classification RNN for NLP (examples: spam detection, sentiment analysis, parts-of-speech tagging, named entity recognition)

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 Tensorflow. 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:

matrix addition, multiplication
basic probability (conditional and joint distributions)
Python coding: if/else, loops, lists, dicts, sets
Numpy coding: matrix and vector operations, loading a CSV file

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

Content

Introduction and Outline

Outline of this Course

Review of Important Deep Learning Concepts

How to Succeed in this Course

Where to get the Code and Data

Preprocessed Wikipedia Data

The Simple Recurrent Unit

Architecture of a Recurrent Unit

Prediction and Relationship to Markov Models

Unfolding a Recurrent Network

Backpropagation Through Time (BPTT)

The Parity Problem - XOR on Steroids

The Parity Problem in Code using a Feedforward ANN

Theano Scan Tutorial

The Parity Problem in Code using a Recurrent Neural Network

On Adding Complexity

Recurrent Neural Networks for NLP

Word Embeddings and Recurrent Neural Networks

Word Analogies with Word Embeddings

Representing a sequence of words as a sequence of word embeddings

Generating Poetry

Generating Poetry in Code (part 1)

Generating Poetry in Code (part 2)

Classifying Poetry

Classifying Poetry in Code

Advanced RNN Units

Rated RNN Unit

RRNN in Code - Revisiting Poetry Generation

Gated Recurrent Unit (GRU)

GRU in Code

Long Short-Term Memory (LSTM)

LSTM in Code

Learning from Wikipedia Data

Alternative to Wikipedia Data: Brown Corpus

Learning from Wikipedia Data in Code (part 1)

Learning from Wikipedia Data in Code (part 2)

Visualizing the Word Embeddings

Batch Training

Batch Training for Simple RNN

TensorFlow

Simple RNN in TensorFlow

Basics Review

(Review) Theano Basics

(Review) Theano Neural Network in Code

(Review) Tensorflow Basics

(Review) Tensorflow Neural Network in Code

Appendix / FAQ

What is the Appendix?

How to install wp2txt or WikiExtractor.py

Windows-Focused Environment Setup 2018

How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow

How to Code by Yourself (part 1)

How to Code by Yourself (part 2)

How to Succeed in this Course (Long Version)

Is this for Beginners or Experts? Academic or Practical? Fast or slow-paced?

Proof that using Jupyter Notebook is the same as not using it

BONUS: Where to get Udemy coupons and FREE deep learning material

Python 2 vs Python 3

Is Theano Dead?

What order should I take your courses in? (part 1)

What order should I take your courses in? (part 2)

Screenshots

Deep Learning: Recurrent Neural Networks in Python - Screenshot_01

Deep Learning: Recurrent Neural Networks in Python - Screenshot_02

Deep Learning: Recurrent Neural Networks in Python - Screenshot_03

Deep Learning: Recurrent Neural Networks in Python - Screenshot_04

Reviews

Shree

October 25, 2023

This course contains a lot of information that is quite useful for sequence modeling, time series forecasting, and NLP. Thanks to this course, it allows me to understand the fundamentals of RNNs and appreciate its application.

Oussama

October 17, 2023

the course contain a tremendous amount of useful information that can help in understanding what's going on under the hood, which is nice and good as a start.

Umesh

September 23, 2023

Superb course, very detailed step by step, lots of exercises to go through all aspects. Thank you Lazy Programmer!

Arjun

August 28, 2023

Fantastic course. The pacing is great and a lot of the basic principles are really hammered in as you get to watch and then practice everything.

Ahmed

May 22, 2023

There are a lot of keywords used with no explanation, like for example shape in the Input layer. and it wasn't clear why we did the model compilation and what is doing. otherwise, the lecture was awesome, I learned many things useful. Thanks to the lecturer and his hard effort

Karen

May 6, 2023

Really interesting course that covers a lot of ground. Easy to follow along with the code and explanations. Now I know what RNNs can do!

Chuck

March 7, 2023

110% worth your money. At first I thought it might be a little slow considering I am already trained in linear regression and classification and wanted to start learning deep learning right away, but after going through the whole course, there is something here for every skill level. What made this course stand out is that he doesn't just show you some library code, he also went deep into the theory on how neural networks learn and how each architecture actually works, and even more importantly, how to properly apply them to real-world datasets. Totally worth the money and I only wish I'd heard of it sooner.

Sanjay

February 24, 2023

I had fun learning throughout the course. Everything is detailed and resources are abundant. The stock prediction exercise was eye opening.

Hongqian

October 26, 2022

I haven't finished the course but the instructor is very humorous. It's entertaining to watch these videos. LOL

Joaquin

October 20, 2022

It is very well explained, it goes in detail without getting complicated and it is easy to understand.

Anuj

October 8, 2022

It was a fantastic learning and briefing on Tensorflow for RNNs and deep learning. I would recommend this course for all who start with basics of deep learning. Thank you @LazyProgrammer

Kurt

September 14, 2022

So far so good. I'm concerned that being dismissive of people who might need all the resources (ie: Colab), due to a conflict between the author's teaching style (visual/audio) and their own learning style (kinesthetic), may be counterproductive - but I'm holding that in abeyance for now.

NISHANT

August 30, 2022

Good intuitive explanation of LSTMs and GRU. Makes more sense. Examples are badly chosen and nothing gives a good convergence and does not really show realworld use case

Consulenti.Formazione1

August 28, 2022

Credo di aver scoperto alcune cose interessanti che potrebbero rendersi utili anche in un prossimo futuro

Jonathan

August 4, 2022

I really enjoyed this course. It explained in details the concept of LSTM. It was a great help as it helped me to successfully complete my masters thesis.

Charts

Price

Rating

Enrollment distribution

Deep Learning: Recurrent Neural Networks in Python - Distribution chart