Machine Learning and Deep Learning Using TensorFlow

Artificial Intelligence (AI): Machine Learning, Deep Neural Networks (DNN), and Convolution Neural Networks (CNN)

4.90 (45 reviews)
Udemy
platform
English
language
Data Science
category
instructor
Machine Learning and  Deep Learning Using TensorFlow
608
students
10 hours
content
Apr 2022
last update
$79.99
regular price

What you will learn

In depth understanding of Machine Learning.

In depth understanding of the Neural Network.

Detailed and step by step theoretical derivation and explanation of a majority of the topics to ensure clear understanding of the subject.

You will learn Linear Regression, Logistic Regression, Neural Network, Deep Neural Network (DNN), Convolution Neural Network etc.

Multiple hands-on projects using Tensorflow 2 and Python to expose you to some of the highly advanced topics of Tensorflow 2

Hands-on projects are selected to make you familiar with some of the expertise that may be very useful should you need to run a very long analysis in future.

Description

If you are interested in Machine Learning, Neural Networks, Deep Learning, Deep Neural Networks (DNN), and Convolution Neural Networks (CNN) with an in-depth and clear understanding, then this course is for you.

Topics are explained in detail. Concepts are developed progressively in a step by step manner. I sometimes spent more than 10 minutes discussing a single slide instead of rushing through it. This should help you to be in sync with the material presented and help you better understand it.

The hands-on examples are selected primarily to make you familiar with some aspects of TensorFlow 2 or other skills that may be very useful if you need to run a large and complex neural network job of your own in the future.

Hand-on examples are available for you to download.

Please watch the first two videos to have a better understanding of the course.


TOPICS COVERED


  • What is Machine Learning?


  • Linear Regression

  • Steps to Calculate the Parameters

  • Linear Regression-Gradient Descent using Mean Squared Error (MSE) Cost Function


  • Logistic Regression: Classification

  • Decision Boundary

  • Sigmoid Function

  • Non-Linear Decision Boundary

  • Logistic Regression: Gradient Descent

  • Gradient Descent using Mean Squared Error Cost Function

  • Problems with MSE Cost Function for Logistic Regression

  • In Search for an Alternative Cost-Function

  • Entropy and Cross-Entropy

  • Cross-Entropy: Cost Function for Logistic Regression

  • Gradient Descent with Cross Entropy Cost Function

  • Logistic Regression: Multiclass Classification


  • Introduction to Neural Network

  • Logical Operators

  • Modeling Logical Operators using Perceptron(s)

  • Logical Operators using Combination of Perceptron

  • Neural Network: More Complex Decision Making

  • Biological Neuron

  • What is Neuron? Why Is It Called the Neural Network?

  • What Is An Image?

  • My “Math” CAT. Anatomy of an Image

  • Neural Network: Multiclass Classification

  • Calculation of Weights of Multilayer Neural Network Using Backpropagation Technique

  • How to Update the Weights of Hidden Layers using Cross Entropy Cost Function


  • Hands On

  • Google Colab. Setup and Mounting Google Drive (Colab)

  • Deep Neural Network (DNN) Based Image Classification Using Google Colab. & TensorFlow (Colab)


  • Introduction to Convolution Neural Networks (CNN)

  • CNN Architecture

  • Feature Extraction, Filters, Pooling Layer

  • Hands On

  • CNN Based Image Classification Using Google Colab & TensorFlow (Colab)


  • Methods to Address Overfitting and Underfitting Problems

  • Regularization, Data Augmentation, Dropout, Early Stopping

  • Hands On

  • Diabetes prediction model development (Colab)

  • Fixing problems using Regularization, Dropout, and Early Stopping (Colab)


  • Hands On: Various Topics

  • Saving Weights and Loading the Saved Weights (Colab)

  • How To Split a Long Run Into Multiple Smaller Runs

  • Functional API and Transfer Learning (Colab)

  • How to Extract the Output From an Intermediate Layer of an Existing Model (Colab), and add additional layers to it to build a new model.

Content

Introduction

Introduction
Topics Covered

What is Machine Learning?

What is Machine Learning?

Linear Regression

Steps to Calculate the Parameters
Gradient Descent using Mean Squared Error Cost Function
Linear Regression: Simple Example

Logistic Regression: Classification

Classification, Decision Boundary, and Perceptron
Decision Boundary and Sigmoid Function
Contd: Decision Boundary and Sigmoid Function
Logistic Regression: Gradient Descent

In Search for an Alternative Cost-Function

Introduction to Entropy
Introduction to Cross-Entropy
Cross-Entropy (contd.)
Cross-Entropy Cost Function
Gradient Descent with Cross Entropy Cost Function
Logistic Regression: Multiclass Classification

Introduction to Neural Network

Logical Operators
Modeling Logical Operators using Perceptron(s)
Biological Neuron
What Is An Image?
Neural Network: Multiclass Classification
Calculation of Weights Using Backpropagation Technique
How to Update the Weights of Hidden Layers using Cross Entropy Cost Function
Update the Weights of Hidden Layers using Cross Entropy Cost Function (contd)
Sigmoid to ReLU for Inner Layer, Softmax for Output Layer
What are Softmax and ReLU activation function?

For download: All Colab files for hands-on

Files for download to your computer, and then upload to your google drive to run

Google Colab. Setup, Mounting Google Drive and Hands On

Google Colab. Setup and Mounting Google Drive
Deep Neural Network (DNN) Based Image Classification
DNN Based Image Classification Using Google Colab. & TensorFlow

Introduction to Convolution Neural Networks (CNN)

CNN: Feature Extraction
CNN: Feature Extraction (Contd.)
Hands On: CNN Based Image Classification Using Google Colab & TensorFlow

Regularization, Dropout, and Early Stopping

Methods to Address Overfitting and Underfitting Problems
Regularization, Dropout, and Early-Stopping
Hands On: Regularization, Dropout, and Early Stopping

Hands On: Various Topics

Saving Weights and Loading the Saved Weights
How To Split a Long Run Into Multiple Smaller Runs
Functional API and Transfer Learning
How to Extract the Output From an Intermediate Layer of an Existing Model

Reviews

Sushila
September 8, 2022
I thought it was a great course covering the basics of machine learning and I really enjoyed the presentation style!
Neel
May 30, 2022
Pretty nice course. I particularly liked how the concept of entropy/cross-entropy explained, and also the detailed mathematical explanation of back propagation techniques. Hands-on examples are quite useful.
David
April 26, 2022
I am looking forward to the in depth explanation of the machine learning concepts covered in this course, and to gaining a more full understanding of these tools instead of simply being told how to use them (but not why).
Sayantika
April 19, 2022
Will recommend this course for its lucid explanation of the topics and byte size learning modules for each concept.
GoutamMajumdar
April 19, 2022
Although a bit mathematical, it’s nicely covered all the aspects in details and also well narrated. Excellent work !
Prabhat
April 14, 2022
This is a great course to get a complete understanding of machine learning. The course starts with simple concepts and then progresses to explain more complex calculations. The hands on exercise is very helpful and shows theory in action.
Asis
April 12, 2022
It was very well organized and well-thought coursework. Looking at the depth of the content, I can certainly say that a lot of research work was done by the presenter/creator. 1) I like the hands-on examples of this course. Last year I was working on a personal project and the main problem I had was dealing with long run time that got disrupted for various reasons. This course discussed many hand-on projects that showed how to deal with long analysis projects. That is very helpful. Also, this course really focused on many small details. 2) I have taken many machine learning courses but none explains the core concept clearly. Although a bit mathematical, this course really explained the core concept of machine learning and neural networks nicely. You will clearly understand what is going on. I also liked the hands-on part because the approach is quite different. I really like it.
Jaya
April 10, 2022
This course really explained the concept very well. The presentation style is very natural. This is a no-frill course. Instructor straight dived into the topic. This course actually goes to the core of the topic and explains it This course is somewhat mathematical and the instructor derives and shows mathematically what he is talking about. So, if you are comfortable with math, this course will greatly help you to understand the subject.

Charts

Price

Machine Learning and  Deep Learning Using TensorFlow - Price chart

Rating

Machine Learning and  Deep Learning Using TensorFlow - Ratings chart

Enrollment distribution

Machine Learning and  Deep Learning Using TensorFlow - Distribution chart
4608854
udemy ID
3/23/2022
course created date
5/15/2022
course indexed date
Bot
course submited by