4.36 out of 5
4.36
201 reviews on Udemy

Tensorflow and Keras For Neural Networks and Deep Learning

Master the Most Important Deep Learning Frameworks (Tensorflow & Keras) for Python Data Science
Instructor:
Minerva Singh
9,414 students enrolled
English [Auto-generated]
Harness The Power Of Anaconda/iPython For Practical Data Science
Learn How To Install & Use Tensorflow Within Anaconda
Implement Statistical & Machine Learning With Tensorflow
Implement Neural Network Modelling With Tensorflow & Keras
Implement Deep Learning Based Unsupervised Learning With Tensorflow and Keras
Implement Deep Learning Based Supervised Learning With Tensorflow & Keras
Implement Convolution Neural Networks With Tensorflow & Keras

THIS IS A COMPLETE NEURAL NETWORKS & DEEP LEARNING TRAINING WITH TENSORFLOW & KERAS IN PYTHON!

It is a full 7-Hour Python Tensorflow & Keras Neural Network & Deep Learning Boot Camp that will help you learn basic machine learning, neural networks and deep learning  using two of the most important Deep Learning frameworks- Tensorflow and Keras.                         

HERE IS WHY YOU SHOULD ENROLL IN THIS COURSE:

This course is your complete guide to practical machine & deep learning using the Tensorflow & Keras framework in Python..

This means, this course covers the important aspects of Keras and Tensorflow (Google’s powerful Deep Learning framework) and if you take this course, you can do away with taking other courses or buying books on Python Tensorflow and Keras based data science.  

In this age of big data, companies across the globe use Python to sift through the avalanche of information at their disposal and advent of Tensorflow and Keras is revolutionizing Deep Learning…

By gaining proficiency in Keras and and Tensorflow, you can give your company a competitive edge and boost your career to the next level.

THIS IS MY PROMISE TO YOU: COMPLETE THIS ONE COURSE & BECOME A PRO IN PRACTICAL KERAS & TENSORFLOW BASED DATA SCIENCE!

But first things first. My name is Minerva Singh and I am an Oxford University MPhil (Geography and Environment) graduate. I recently finished a PhD at Cambridge University (Tropical Ecology and Conservation).

I have several years of experience in analyzing real life data from different sources  using data science related techniques and producing publications for international peer reviewed journals.

 Over the course of my research I realized almost all the Python data science courses and books out there do not account for the multidimensional nature of the topic and use data science interchangeably with machine learning..

This gives students an incomplete knowledge of the subject. My course, on the other hand, will give you a robust grounding in all aspects of data science within the Tensorflow framework.

Unlike other Python courses, we dig deep into the statistical modeling features of Tensorflow & Keras and give you a one-of-a-kind grounding in these frameworks!

DISCOVER 8 COMPLETE SECTIONS ADDRESSING EVERY ASPECT OF PYTHON BASED TENSORFLOW DATA SCIENCE:

• A full introduction to Python Data Science and powerful Python driven framework for data science, Anaconda
• Getting started with Jupyter notebooks for implementing data science techniques in Python
• A comprehensive presentation about Tensorflow & Keras installation and a brief introduction to the other Python data science packages
• Brief introduction to the working of Pandas and Numpy
• The basics of the Tensorflow syntax and graphing environment
• The basics of the Keras syntax
• Machine Learning, Supervised Learning, Unsupervised Learning in the Tensorflow & Keras frameworks
• You’ll even discover how to create artificial neural networks and deep learning structures with Tensorflow & Keras

BUT,  WAIT! THIS ISN’T JUST ANY OTHER DATA SCIENCE COURSE:

You’ll start by absorbing the most valuable Python Tensorflow and Keras basics and techniques.

I use easy-to-understand, hands-on methods to simplify and address even the most difficult concepts.

My course will help you implement the methods using real data obtained from different sources. Many courses use made-up data that does not empower students to implement Python based data science in real -life.

After taking this course, you’ll easily use packages like Numpy, Pandas, and Matplotlib to work with real data in Python along with gaining fluency in Tensorflow and Keras. I will even introduce you to deep learning models such as Convolution Neural network (CNN) !!

The underlying motivation for the course is to ensure you can apply Python based data science on real data into practice today, start analyzing  data for your own projects whatever your skill level, and impress your potential employers with actual examples of your data science abilities.

This course will take students without a prior Python and/or statistics background background from a basic level to performing some of the most common advanced data science techniques using the powerful Python based Jupyter notebooks

It is a practical, hands-on course, i.e. we will spend some time dealing with some of the theoretical concepts related to data science. However, majority of the course will focus on implementing different  techniques on real data and interpret the results..

After each video you will learn a new concept or technique which you may apply to your own projects!

JOIN THE COURSE NOW!

INTRODUCTION TO THE COURSE: The Key Concepts and Software Tools

1
Introduction to the Course
2
Data and Scripts For the Course
3
Python Data Science Environment
4
For Mac Users
5
Introduction to IPython
6
Install Tensorflow
7
Written Tensorflow Installation Instructions
8
Install Keras on Windows 10
9
Install Keras on Mac
10
Written Keras Installation Instructions

Introduction to Python Data Science Packages

1
Python Packages for Data Science
2
Introduction to Numpy
3
Create Numpy Arrays
4
Numpy Operations
5
Numpy for Statistical Operation
6
Introduction to Pandas
7
Read in Data from CSV
8
Read in Data from Excel
9
Basic Data Cleaning

Introduction to TensorFlow

1
A Brief Touchdown
2
A Brief Touchdown: Computational Graphs
3
Common Mathematical Operators in Tensorflow
4
A Tensorflow Session
5
Interactive Tensorflow Session
6
Constants and Variables in Tensorflow
7
Placeholders in Tensorflow

Introduction to Keras

1
What is Keras

Some Preliminary Tensorflow and Keras Applications

1
Theory of Linear Regression (OLS)
2
OLS From First Principles
3
Visualize the Results of OLS
4
Multiple Regression With Tensorflow-Part 1
5
Estimate With Tensorflow Estimators
6
Multiple Regression With Tensorflow Estimators
7
More on Linear Regressor Estimator
8
GLM: Generalized Linear Model
9
Linear Classifier For Binary Classification
10
Accuracy Assessment For Binary Classification
11
Linear Classification with Binary Classification With Mixed Predictors
12
Softmax Classification With Tensorflow

Some Basic Concepts

1
What is Machine Learning?
2
Theory Behind ANN (Artificial Neural Network) and DNN (Deep Neural Networks)

Unsupervised Learning With Tensorflow and Keras

1
What is Unsupervised Learning?
2
Autoencoders for Unsupervised Classification
3
Autoencoders in Tensorflow (Binary Class Problem)
4
Autoencoders in Tensorflow (Multiple Classes)
5
Autoencoders in Keras (Simple)
6
Autoencoders in Keras (Sparsity Constraints)
7
Deep Autoencoder With Keras

Neural Network for Tensorflow & Keras

1
Multi Layer Perceptron (MLP) with Tensorflow
2
Multi Layer Perceptron (MLP) With Keras
3
Keras MLP For Binary Classification
4
Keras MLP for Multiclass Classification
5
Keras MLP for Regression

Deep Learning For Tensorflow & Keras

1
What is Artificial Intelligence?
2
Deep Neural Network (DNN) Classifier With Tensorflow
3
Deep Neural Network (DNN) Classifier With Mixed Predictors
4
Deep Neural Network (DNN) Regression With Tensorflow
5
Wide & Deep Learning (Tensorflow)
6
DNN Classifier With Keras
7
DNN Classifier With Keras-Example 2

Convolution Neural Network (CNN) For Image Analysis

1
Introduction to CNN
2
Implement a CNN for Multi-Class Supervised Classification
3
Activation Functions
4
More on CNN
5
Pre-Requisite For Working With Imagery Data
6
CNN on Image Data-Part 1
7
CNN on Image Data-Part 2
8
More on TFLearn
9
CNN Workflow for Keras
10
CNN With Keras
11
CNN on Image Data with Keras-Part 1
12
CNN on Image Data with Keras-Part 2

Autoencoders With Convolution Neural Networks (CNN)

1
Autoencoders for With CNN- Tensorflow
2
Autoencoders for With CNN- Keras

Recurrent Neural Networks (RNN)

1
Theory Behind RNNs
2
LSTM For Time Series Data
3
LSTM for Predicting Stock Prices

Miscellaneous Section

1
Use Colabs for Jupyter Data Science
You can view and review the lecture materials indefinitely, like an on-demand channel.
Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don't have an internet connection, some instructors also let their students download course lectures. That's up to the instructor though, so make sure you get on their good side!
4.4
4.4 out of 5
201 Ratings

Detailed Rating

Stars 5
120
Stars 4
39
Stars 3
25
Stars 2
10
Stars 1
10
ded573cd3ad2e929da3fed6ea7b6b88d
30-Day Money-Back Guarantee

Includes

8 hours on-demand video
4 articles
Full lifetime access
Access on mobile and TV
Certificate of Completion