Home Courses Instructor Labs

Tensorflow and Keras For Neural Networks and Deep Learning

(40 Ratings) 2324 Students Enrolled
Created By Aneshwa Singh Last Updated Wed, 03-Jun-2020 English
  • Course Duration
    7 Hours
  • Mode of Training
    Self-Paced
  • Lessons
    70 Lessons
  • Validity
    Life Time
12k+ satisfied learners Read Reviews
What Will I Learn?
  • Learn to implement Statistical & Machine Learning with Tensorflow
  • Implement Deep Learning based Unsupervised learning and Supervised Learning with Tensorflow and Keras
  • Learn to install Tensorflow with Anaconda
  • Learn to implement the Neural Networks Modelling with Tensorflow and Keras
  • Implement the Convolution Neural Networks with Tensorflow and Keras

Requirements
  • Prior Knowledge on Python with Data Science will be helpful
  • Knowledge on Basic Statistical Concepts and Implementations
  • Exposure to Machine Learning terms such as cross-validation
+ View More
Description

In this course, you will be learning the complete Neural Networks & Deep Learning training with Tensorflow & Keras in Python.

Initially you will be learning the basics of machine learning, neural networks and deep learning using the two most famous Deep Learning frameworks such as Tensorflow and Keras.

Tensorflow is the most  famous Google's powerful Deep Learning Framework which along with Keras Frameworks used to learn Neural Networks and Deep Learning. 

In the current era of Big Data, we use Python to sift through the avalanche of information at their disposal. The advent of Tensorflow and Keras are revolutionizing Deep Learning.

By Learning Tensorflow and Keras, you can boost your career to the next level.

The following areas are covered in this course:

  • Introduction on Python Data Science & powerful Python driven framework for Data Science.
  • Get started with Anaconda Jupyter Notebooks for implementing Data Science concepts in Python.
  • Learn the installation of Tensorflow and Keras & the other Python Data Science packages.
  • Work with Pandas and NumPy libraries.
  • Tensorflow syntax basics and graphing environment
  • Baics of Keras syntax
  • Learn on Machine Learning, Supervised Learning, Unsupervised Learning in the Tensorflow and Keras Frameworks.
  • Learn how to create the artificial Neural Networks and Deep Learning structures with Tensorflow and Keras

In this course, you will also learn how to implement the real data obtained from different sources. After completing this course, you can easily use packages like Numpy, Pandas and Matplotlib to work with real data in Python along with Tensorflow and Keras.

Curriculum For This Course
70 Lessons 7 Hours
  • Python Data Science Environment 00:10:58 Preview
  • For Mac Users 00:04:05
  • Introduction to IPython 00:19:14
  • Install Keras on Windows 10 00:05:17
  • Install Keras on Mac 00:04:19
  • Python Packages for Data Science 00:03:16 Preview
  • Introduction to Numpy 00:03:46
  • Create Numpy Arrays 00:10:52
  • Numpy Operations 00:16:49
  • Numpy for Statistical Operation 00:07:23
  • Introduction to Pandas 00:12:07
  • Read in Data from CSV 00:05:43
  • Read in Data from Excel 00:05:32
  • Basic Data Cleaning 00:04:30
  • A Brief Touchdown 00:02:36 Preview
  • A Brief Touchdown: Computational Graphs 00:02:56
  • A Tensorflow Session 00:04:37
  • Interactive Tensorflow Session 00:01:38
  • Constants and Variables in Tensorflow 00:03:42
  • Placeholders in Tensorflow 00:03:59
  • What is Keras 00:03:30 Preview
  • Theory of Linear Regression (OLS) 00:10:45
  • OLS From First Principles 00:09:23
  • Visualize the Results of OLS 00:03:28
  • Multiple Regression With Tensorflow-Part 1 00:05:09
  • Estimate With Tensorflow Estimators 00:03:06
  • Multiple Regression With Tensorflow Estimators 00:05:25
  • More on Linear Regressor Estimator 00:08:25
  • GLM: Generalized Linear Model 00:05:25
  • Linear Classifier For Binary Classification 00:09:34
  • Accuracy Assessment For Binary Classification 00:04:19
  • Linear Classification with Binary Classification With Mixed Predictors 00:08:15
  • Softmax Classification With Tensorflow 00:07:36
  • What is Machine Learning? 00:05:32 Preview
  • Theory Behind ANN (Artificial Neural Network) and DNN (Deep Neural Networks) 00:09:18
  • What is Unsupervised Learning? 00:01:38
  • Autoencoders for Unsupervised Classification 00:01:46
  • Autoencoders in Tensorflow (Binary Class Problem) 00:07:32
  • Autoencoders in Tensorflow (Multiple Classes) 00:05:43
  • Autoencoders in Keras (Simple) 00:05:44
  • Deep Autoencoder With Keras 00:07:39
  • Multi Layer Perceptron (MLP) with Tensorflow 00:06:24
  • Multi Layer Perceptron (MLP) With Keras 00:03:31
  • Keras MLP For Binary Classification 00:04:01
  • Keras MLP for Multiclass Classification 00:06:02
  • Keras MLP for Regression 00:03:28
  • What is Artificial Intelligence? 00:09:51 Preview
  • Deep Neural Network (DNN) Classifier With Tensorflow 00:06:48
  • Deep Neural Network (DNN) Classifier With Mixed Predictors 00:08:12
  • Deep Neural Network (DNN) Regression With Tensorflow 00:05:25
  • Wide & Deep Learning (Tensorflow) 00:11:35
  • DNN Classifier With Keras 00:03:31
  • DNN Classifier With Keras-Example 2 00:04:24
  • Introduction to CNN 00:11:26
  • Implement a CNN for Multi-Class Supervised Classification 00:07:28
  • Activation Functions 00:05:51
  • More on CNN 00:04:36
  • Pre-Requisite For Working With Imagery Data 00:02:34
  • CNN on Image Data-Part 1 00:10:41
  • CNN on Image Data-Part 2 00:06:38
  • More on TFLearn 00:07:54
  • CNN Workflow for Keras 00:04:05
  • CNN With Keras 00:04:10
  • CNN on Image Data with Keras-Part 1 00:02:27
  • CNN on Image Data with Keras-Part 2 00:05:06
  • Autoencoders for With CNN- Tensorflow 00:07:15
  • Autoencoders for With CNN- Keras 00:04:46
  • Theory Behind RNNs 00:05:41
  • LSTM For Time Series Data 00:06:24
  • LSTM for Predicting Stock Prices 00:07:22

Tensorflow and Keras For Neural Networks and Deep Learning