The ‘Complete Guide to TensorFlow for Deep Learning with Python Course’ is a project-based course that teaches students how to use the TensorFlow framework to build Deep Learning models. The course requires students to have basic Python knowledge and know basic mathematical concepts such as standard deviation. It covers the basics of TensorFlow, neural networks, data flow graphs, reinforcement learning, and more.

The course is designed and instructed by Jose Portilla. He has years of experience working with Linux distributions and Unix operating systems. The course is usually available for **INR 2,299** on Udemy but students can click on the link and get the ‘**Complete Guide to TensorFlow for Deep Learning with Python Course**’ for **INR 449**.

## Who all can opt for this course?

Curious students who want to learn the latest Deep Learning techniques using TensorFlow.

## Course Highlights

Key Highlights | Details |
---|---|

Registration Link | Apply Now! |

Price | INR 449 (INR 2,299) 80% off |

Duration | 14 hours |

Rating | 4.2/5 |

Student Enrollment | 93,845 students |

Instructor | Jose Portilla https://www.linkedin.com/in/joseportilla |

Topics Covered | Machine learning, neural networks, TensorFlow basics, convolutional neural networks, recurrent neural networks, etc. |

Course Level | Intermediate (Candidates should know basic Python programming and standard deviations) |

Total Student Reviews | 16,634 |

## Learning Outcomes

- Know how neural networks function
- Create your own neural network from scratch using Python
- Employ TensorFlow for tasks involving regression and classification
- Convolutional neural networks for image classification using TensorFlow
- Recurrent neural networks for time series analysis using TensorFlow
- Utilize TensorFlow to use AutoEncoders to solve unsupervised learning issues
- Use OpenAI Gym to learn how to apply reinforcement learning
- Use TensorFlow to build generative adversarial networks
- Become an expert in deep learning

## Course Content

S.No. | Module (Duration) | Topics |
---|---|---|

1. | Introduction (12 minutes) | Introduction |

Course Overview — PLEASE DON’T SKIP THIS LECTURE! Thanks 🙂 | ||

FAQ – Frequently Asked Questions | ||

2. | Installation and Setup (12 minutes) | Quick Note for MacOS and Linux Users |

Installing TensorFlow and Environment Setup | ||

3. | What is Machine Learning? (17 minutes) | Machine Learning Overview |

4. | Crash Course Overview (45 minutes) | Crash Course Section Introduction |

NumPy Crash Course | ||

Pandas Crash Course | ||

Data Visualization Crash Course | ||

SciKit Learn Preprocessing Overview | ||

Crash Course Review Exercise | ||

Crash Course Review Exercise – Solutions | ||

5. | Introduction to Neural Networks (01 hour 17 minutes) | Introduction to Neural Networks |

Introduction to Perceptron | ||

Neural Network Activation Functions | ||

Cost Functions | ||

Gradient Descent Backpropagation | ||

TensorFlow Playground | ||

Manual Creation of Neural Network – Part One | ||

Manual Creation of Neural Network – Part Two – Operations | ||

Manual Creation of Neural Network – Part Three – Placeholders and Variables | ||

Manual Creation of Neural Network – Part Four – Session | ||

Manual Neural Network Classification Task | ||

6. | TensorFlow Basics (02 hours 39 minutes) | Introduction to TensorFlow |

TensorFlow Basic Syntax | ||

TensorFlow Graphs | ||

Variables and Placeholders | ||

TensorFlow – A Neural Network – Part One | ||

TensorFlow – A Neural Network – Part Two | ||

TensorFlow Regression Example – Part One | ||

TensorFlow Regression Example _ Part Two | ||

TensorFlow Classification Example – Part One | ||

TensorFlow Classification Example – Part Two | ||

TF Regression Exercise | ||

TF Regression Exercise Solution Walkthrough | ||

TF Classification Exercise | ||

TF Classification Exercise Solution Walkthrough | ||

Saving and Restoring Models | ||

7. | Convolutional Neural Networks (02 hours 09 minutes) | Introduction to Convolutional Neural Network Section |

Review of Neural Networks | ||

New Theory Topics | ||

Quick note on MNIST lecture | ||

MNIST Data Overview | ||

MNIST Basic Approach Part One | ||

MNIST Basic Approach Part Two | ||

CNN Theory Part One | ||

CNN Theory Part Two | ||

CNN MNIST Code Along – Part One | ||

CNN MNIST Code Along – Part Two | ||

Introduction to CNN Project | ||

CNN Project Exercise Solution – Part One | ||

CNN Project Exercise Solution – Part Two | ||

8. | Recurrent Neural Networks (02 hours 38 minutes) | Introduction to RNN Section |

RNN Theory | ||

Manual Creation of RNN | ||

Vanishing Gradients | ||

LSTM and GRU Theory | ||

Introduction to RNN with TensorFlow API | ||

RNN with TensorFlow – Part One | ||

RNN with TensorFlow – Part Two | ||

Quick Note on RNN Plotting Part 3 | ||

RNN with TensorFlow – Part Three | ||

Time Series Exercise Overview | ||

Time Series Exercise Solution | ||

Quick Note on Word2Vec | ||

Word2Vec Theory | ||

Word2Vec Code Along – Part One | ||

Word2Vec Part Two | ||

9. | Miscellaneous Topics (53 minutes) | Intro to Miscellaneous Topics |

Deep Nets with Tensorflow Abstractions API – Part One | ||

Deep Nets with Tensorflow Abstractions API – Estimator API | ||

Deep Nets with Tensorflow Abstractions API – Keras | ||

Deep Nets with Tensorflow Abstractions API – Layers | ||

Tensorboard | ||

10. | AutoEncoders (54 minutes) | Autoencoder Basics |

Dimensionality Reduction with Linear Autoencoder | ||

Linear Autoencoder PCA Exercise Overview | ||

Linear Autoencoder PCA Exercise Solutions | ||

Stacked Autoencoder | ||

11. | Reinforcement Learning with OpenAI Gym (01 hour 27 minutes) | Introduction to Reinforcement Learning with OpenAI Gym |

Extra Resources for Reinforcement Learning | ||

Introduction to OpenAI Gym | ||

OpenAI Gym Steup | ||

Open AI Gym Env Basics | ||

Open AI Gym Observations | ||

OpenAI Gym Actions | ||

Simple Neural Network Game | ||

Policy Gradient Theory | ||

Policy Gradient Code Along Part One | ||

Policy Gradient Code Along Part Two | ||

12. | GAN – Generative Adversarial Networks (39 minutes) | Introduction to GANs |

GAN Code Along – Part One | ||

GAN Code Along – Part Two | ||

GAN Code Along – Part Three | ||

13. | BONUS (10 seconds) | Bonus Lecture |

## Resources Required

- Basic Python programming
- Basic math (mean, standard deviation, etc.)

## Featured Review

**Navneet Singh (5/5)**: I like the pace so far. It gets confusing sometimes in between but you cannot blame the instructor for that as the topic in itself is quite complicated in few places. Having said that, the instructor does try his best to simplify the explanations.

## Pros

**Michael Brownfield (5/5)**: Excellent Course! Provides everything that is needed to get you running.**Rick Vink (5/5)**: All the networks (RNN, CNN, Autoencoder and GANs) that I definitly wanted to know are included so great course!**Jonas Stepanik (5/5)**: Thank you for this awesome course Here is my github: https://github.com/Fable67**Ismalia Bouba (5/5)**: Excellent, i will recommend this to any data scientist out there.

## Cons

**Bill Sheppard (1/5)**: This makes all of the labs COMPLETELY BROKEN! Plenty of users asking for it to be updated but the Author has been unresponsive.**Duddu Venkata sai ayyappa hemanth (1/5)**: This is too bad.!!! That’s why I shifted to coursera, they are giving back the help within hours.**Emanuel Hernandez (1/5)**: I have been programming for 4 years now and it is still so difficult to see what he is doing.**Robbe Vanhaesebroeck (1/5)**: This course teaches Tensorflow 1.0 which by now is completely outdated.

## About the Author

The instructor of this course is Jose Portilla who is the head of the Data Science department at Pierian Training. With a 4.6 instructor rating and 1,021,912 reviews on Udemy, he offers 60 courses and has taught 3,289,015 students so far.

- Jose Portilla holds degrees in mechanical engineering from Santa Clara University (BS and MS), and he has years of experience working as a qualified instructor and trainer for Python programming, machine learning, and data science.
- He has written articles and received patents in a number of disciplines, including data science, materials science, and microfluidics.
- He has acquired a set of abilities for data analysis throughout the course of his career, and he wants to combine both his teaching and data science knowledge to educate others on the power of programming, how to analyse data, and how to display the data in attractive visualisations.
- He currently serves as the head of Data Science for Pierian Training, where he trains people at prestigious organisations like General Electric, Cigna, The New York Times, Credit Suisse, McKinsey, and others in data science and python programming on-site.

## Comparison Table

Parameters | Complete Guide to TensorFlow for Deep Learning with Python | Data Science: Modern Deep Learning in Python | Data Science: Deep Learning and Neural Networks in Python |
---|---|---|---|

Offers | INR 449 ( 80% off | INR 455 (87% off | INR 455 (87% off |

Duration | 14 hours | 11.5 hours | 12 hours |

Rating | 4.2/5 | 4.7 /5 | 4.7 /5 |

Student Enrollments | 93,845 | 33,610 | 52,689 |

Instructors | Jose Portilla | Lazy Programmer Inc. | Lazy Programmer Inc. |

Register Here | Apply Now! | Apply Now! | Apply Now! |

## Leave feedback about this