Data Science

The ‘Deep Learning: Recurrent Neural Networks in Python Course’ focuses on Recurrent Neural Networks (RNN). Students will learn how to build an RNN using TensorFlow 2 and how to use GRU and LSTM in it. They will also learn how to predict stock prices and do time series forecasting using TensorFlow 2.

The course is suitable for students who know basic math and have some experience with Python, Numpy, and Matplotlib. The course is usually available for INR 2,799 on Udemy but students can click on the link and get the ‘Deep Learning: Recurrent Neural Networks in Python Course’ for INR 449.

Who all can opt for this course?

  • Students or professionals who want to learn Deep Learning, Time Series Forecasting, Sequence Data, or NLP.
  • Data scientists and software engineers looking to upskill and advance their careers.

Course Highlights

Key HighlightsDetails
Registration LinkApply Now!
PriceINR 449 (INR 2,79984% off
Duration13 hours
Student Enrollment32,596 students
InstructorLazy Programmer Inc.
Topics CoveredMachine learning, neurons, classification, regression, time series data, etc.
Course LevelAdvanced (Students must have prior knowledge of Python, Numpy, Matplotlib and basic math)
Total Student Reviews4,399

Learning Outcomes

  • Time series forecasting using RNNs (tackle the ubiquitous “Stock Prediction” problem)
  • Use RNNs for Text Classification (Spam Detection) and Natural Language Processing (NLP)
  • Apply RNNs for Image Classification
  • Learn about the GRU, LSTM (long short-term memory unit), and simple recurrent unit (Elman unit)
  • Create multiple recurrent networks in TensorFlow 2
  • Learn how to mitigate the vanishing gradient issue

Course Content

S.No.Module (Duration)Topics
1.Welcome (35 minutes)Introduction and Outline
Get Your Hands Dirty, Practical Coding Experience, Data Links
How to use Github & Extra Coding Tips (Optional)
Where to get the code, notebooks, and data
How to Succeed in this Course
2.Google Colab (44 minutes)Intro to Google Colab, how to use a GPU or TPU for free
Uploading your own data to Google Colab
Where can I learn about Numpy, Scipy, Matplotlib, Pandas, and Scikit-Learn?
3.Machine Learning and Neurons (02 hours 05 minutes)Review Section Introduction
What is Machine Learning?
Code Preparation (Classification Theory)
Classification Notebook
Code Preparation (Regression Theory)
Regression Notebook
The Neuron
How does a model “learn”?
Making Predictions
Saving and Loading a Model
Suggestion Box
4.Feedforward Artificial Neural Networks (01 hour 36 minutes)Artificial Neural Networks Section Introduction
Forward Propagation
The Geometrical Picture
Activation Functions
Multiclass Classification
How to Represent Images
Code Preparation (ANN)
ANN for Image Classification
ANN for Regression
5.Recurrent Neural Networks, Time Series, and Sequence Data (03 hours 13 minutes)Sequence Data
Autoregressive Linear Model for Time Series Prediction
Proof that the Linear Model Works
Recurrent Neural Networks
RNN Code Preparation
RNN for Time Series Prediction
Paying Attention to Shapes
GRU and LSTM (pt 1)
GRU and LSTM (pt 2)
A More Challenging Sequence
Demo of the Long Distance Problem
RNN for Image Classification (Theory)
RNN for Image Classification (Code)
Stock Return Predictions using LSTMs (pt 1)
Stock Return Predictions using LSTMs (pt 2)
Stock Return Predictions using LSTMs (pt 3)
Other Ways to Forecast
6.Natural Language Processing (NLP) (40 minutes)Embeddings
Code Preparation (NLP)
Text Preprocessing
Text Classification with LSTMs
7.In-Depth: Loss Functions (23 minutes)Mean Squared Error
Binary Cross Entropy
Categorical Cross Entropy
8.In-Depth: Gradient Descent (54 minutes)Gradient Descent
Stochastic Gradient Descent
Variable and Adaptive Learning Rates
Adam (pt 1)
Adam (pt 2)
9.Extras (01 second)Data Links
10.Setting Up Your Environment (FAQ by Student Request) (37 minutes)Anaconda Environment Setup
How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow
11.Extra Help With Python Coding for Beginners (FAQ by Student Request) (55 minutes)Beginner’s Coding Tips
How to Code by Yourself (part 1)
How to Code by Yourself (part 2)
Proof that using Jupyter Notebook is the same as not using it
Python 2 vs Python 3
12.Effective Learning Strategies for Machine Learning (FAQ by Student Request) (59 minutes)How to Succeed in this Course (Long Version)
Is this for Beginners or Experts? Academic or Practical? Fast or slow-paced?
Machine Learning and AI Prerequisite Roadmap (pt 1)
Machine Learning and AI Prerequisite Roadmap (pt 2)
13.Appendix / FAQ Finale (08 minutes)What is the Appendix?

Resources Required

  • Basic understanding of probability, matrix arithmetic, and derivatives
  • Python, Matplotlib, and Numpy

Featured Review

Harsh Shah (5/5): One of the best courses about the fundamentals of RNNs. It caters to newcomers and experts alike. This is a course anyone with a good background in Python data science programming can take.


  • Joseph French (5/5): This course is impressive in the details it goes into about recurrent neural networks.
  • Shing Sung (5/5): One of the best courses on the fundamentals of recurrent networks.
  • Scott Lustig (5/5): Best class to simultaneously learn about a great emerging ML framework while picking up theano en route.
  • Guiren Sun (5/5): I took this course just to see what LSTMs are all about, but it turned out to be a great course.


  • Ellie Biessek (1/5): Concepts that I already seen in the other course are explained so badly here that I rather just get confused than improve
  • Prudvi Raj Kummari (1/5): all that code is useless if the concepts are not clearly explained.
  • Deven Madan (1/5): If you’re looking for the basics of machine learning with a slight focus on RNNs this is for you.

About the Author

The instructor of this course is Lazy Programmer Inc. who is an artificial intelligence and machine learning engineer. With a 4.6 instructor rating and 1,48,419 reviews on Udemy, he offers 33 courses and has taught 5,27,200 students so far.

  • Although he has also been recognised as a data scientist, big data engineer, and full stack software engineer, he currently spends the majority of his time as an artificial intelligence and machine learning engineer with an emphasis on deep learning.
  • He earned his first master’s degree in computer engineering with a focus on machine learning and pattern recognition more than ten years ago.
  • He later pursued a master’s degree in statistics with a focus on financial engineering.
  • He has previously worked as a data scientist (optimising click and conversion rates) and big data engineer (and building data processing pipelines) with experience in online advertising and digital media.
  • He routinely uses big data technologies like Hadoop, Pig, Hive, MapReduce, and Spark.
  • He has developed deep learning models for text modelling, image and signal processing, user behaviour prediction, and click-through rate estimation.
  • He has taught students at universities like Columbia University, NYU, Hunter College, and The New School.

Comparison Table

ParametersDeep Learning: Recurrent Neural Networks in PythonArtificial Intelligence: Reinforcement Learning in PythonAdvanced AI: Deep Reinforcement Learning in Python
OffersINR 449 (INR 2,799) 84% offINR 455 (INR 3,499) 87% offINR 455 (INR 3,499) 87% off
Duration13 hours14.5 hours10.5 hours
Rating4.6/54.8 /54.6 /5
Student Enrollments32,59343,64736,737
InstructorsLazy Programmer Inc.Lazy Programmer TeamLazy Programmer Team
Register HereApply Now!Apply Now!Apply Now!

Leave feedback about this

  • Rating