Implement ML using TensorFlow 2.3 (Apr 2023)

Name: Implement ML using TensorFlow 2.3 (Apr 2023)
Rating: 4.1 (18 reviews)

Running ML Algorithms using Tensorflow with Google Colab

Created byProton Expert Systems & Solutions

Last updated 9/2023

English

What you'll learn

Introduction to TensorFlow
Introduction to Google Colaboratory (Colab)
Classification and Regression Mechanism
Neural networks and implementation of neural network
Recommender System
Transfer Learning and Fine Tuning
Implementation of Deep convolutional GAN
Implementation of Cycle GAN

Course content

8 sections • 22 lectures • 2h 4m total length

Introduction5:03
This course teaches implementing Machine Learning and Deep Learning concepts using Tensorflow in Google Colaboratory.

Lesson 1: Introduction to TensorFlow and Google Colaboratory5:37
In this lesson, you will learn an overview of TensorFlow and its key features. Discussed the types of tensors and the advantages of using TensorFlow. Further, you will understand the application of TensorFlow that is illustrated and the introduction about Google Colaboratory (Colab).
Practice 1-1: Set up Google Colaboratory for TensorFLow2:16
In this practice, you will learn to set up Google Colaboratory (Colab) Notebook on Google Drive.
Practice 1-2: Creating and Running Simple Applications using TensorFlow2:37
In this practice, you will learn to create and run a simple program in Colab Notebook using TensorFlow.
Quiz on TensorFlow and Google Colaboratory Concepts

Lesson 2: Implementing Classification and Regression using TensorFlow7:32
In this lesson, you’ll learn what is classification and the types of classification. You will explore the Steps to perform classification and regression. You will get to know what is regression and types of regression and further the Advantages of classification and regression.
Practice 2-1: Implement ML Application using Linear Classification Mechanism4:56
In this practice, you will learn to develop and run the linear classification application in Colab Notebook using TensorFlow.
Practice 2-2: ML Application using Linear Regression Mechanism8:36
In this practice, you will learn to develop and run the linear regression application to predict fuel efficiency in Colab Notebook using TensorFlow.
Quiz on Classification and Regression using TensorFlow

Lesson 3: Neural Networks and Artificial Neural Network (ANN)6:07
In this lesson, you will get to know about Neural Network and types of Neural Network. You’ll also learn about ANN and its characteristics. Besides, you will explore the Architecture of ANN and how to build Image classification and Regression using ANN mechanism. Further, you’ll also understand about advantages and applications of ANN.
Practice 3-1: Implementing Image Classification Application using ANN3:38
In this practice, you will learn to develop and run the image classification application using ANN algorithm.
Practice 3-2: Implementing Logistic Regression Application using ANN4:04
In this practice, you will learn to develop and run FeedForward Neural Network with respect to cosine function application using ANN algorithm.
Quiz on Neural Networks and Artificial Neural Network (ANN)

Lesson 4: Recurrent Neural Network (RNN) and Time Series Prediction4:31
In this lesson, you’ll study about RNN and its architecture. You’ll learn to build time series prediction and image classification using RNN mechanism. You will get to know the advantages of using RNN and applications of RNN.
Practice 4-1: Implementing Time Series Prediction using RNN6:03
In this practice, you will learn to develop and run the autoregressive linear model for time series prediction application with respect to sinusoidal wave using RNN algorithm.
Practice 4-2: Implementing Image Classification using RNN3:56
In this practice, you will learn to develop and run the image classification application using RNN algorithm.
Quiz on Recurrent Neural Network (RNN) and Time Series Prediction

Lesson 5: Working with Convolution Neural Network (CNN)5:23
In this lesson, you’ll learn about CNN and its architecture. You will explore on how to build model for colour images using CNN algorithm. Also, you will get to know the advantages and applications of CNN. Bringing out the difference between ANN, CNN and RNN.
Practice 5-1: Implementing CIFAR-10 Application using CNN4:10
In this practice, you will learn to develop and run classification with respect to CIFAR-10 using CNN algorithm.
Practice 5-2: Implementing Fashion MNIST Application using CNN4:28
In this practice, you will learn to develop and run classification with respect to Fashion MNIST application using CNN algorithm.
Quiz on Convolution Neural Network (CNN) and its working

Lesson 6: Recommender System, Transfer Learning and Fine Tuning7:22
In this lesson, you will learn about Recommender system with an example, different ways to approach recommender system and the Steps for building recommender system. Besides, you will get to know about the Transfer learning and steps to perform transfer leaning. Also, about the Fine tuning and steps to perform fine tuning.
Practice 6-1: Implement Recommender Systems using Deep Learning Concept6:02
In this practice, you will learn to develop and run recommender systems using regression technique.
Practice 6-2: Working with Transfer Leaning and Fine Tuning11:07
In this practice, you will learn to develop and run classification using transfer learning and fine tuning techniques from a pre-trained network.
Quiz on Recommender System, Transfer Learning and Fine Tuning

Lesson 7: Generative Adversarial Network (GAN)8:52
In this lesson, you’ll learn about GAN, Generator, Discriminator. You will further understand the working of generator and discriminator. You will get to know the Architecture of GAN. Besides, you’ll also learn about GAN and implementing DCGAN and CycleGAN, Pros and cons of GAN and explore the applications of GAN.
Practice 7-1: Implement DCGAN for Digit MNIST Dataset5:31
In this practice, you will learn to develop and implement DCGAN for digit MNIST dataset.
Practice 7-2: Implement CycleGAN for Translating the Images6:38
In this practice, you will learn to translate the image from horse to zebra using CycleGAN.
Quiz on Generative Adversarial Network (GAN)

Requirements

Basics of Machine Learning
Python (Scipy, Scikit, Matplotlib, Pandas)
Working knowledge on Jupyter Notebook

Description

This course takes you through hands-on approach with TensorFlow using Google Colab.

In this course you will have an overview of TensorFlow. TensorFlow is an open source software library released by Google. It is a Python library/framework which allows developers to express arbitrary computation as data flow graph and for easy calculation of complex mathematical expressions.

Here you will look upon TensorFlow architecture, Advantages and benefits of TensorFlow. You will also explore on Neural networks and implementation, types of neural Network in depth using Classification and regression mechanism. Also learn and understand about the advantages and benefits of using neural networks in brief.

Further, you will learn what is recommender system with an example and different ways to approach recommender system. Besides, you will also get to know the importance of recommender system.

You will explore on how to perform transfer learning on building the model and how to fine tune it. Additionally, you will have a brief overview about GAN (Generative adversarial Network)

Our focus is to teach topics that flow smoothly. The course teaches you everything you need to know about Implementation of ML using TensorFlow 2.3 with hands-on examples.

Every day is a missed opportunity.

Hurry Up

Who this course is for:

Data Scientists
Machine Learning Developers
Big Data Developers

Implement ML using TensorFlow 2.3 (Apr 2023)

What you'll learn

Explore related topics

Course content

Introduction1 lecture • 5min

Introduction to TensorFlow and Google Colaboratory3 lectures • 11min

Implementing Classification and Regression using TensorFlow3 lectures • 21min

Neural Networks and Artificial Neural Network (ANN)3 lectures • 14min

Recurrent Neural Network (RNN) and Time Series Prediction3 lectures • 15min

Working with Convolution Neural Network (CNN)3 lectures • 14min

Recommender System, Transfer Learning and Fine Tuning3 lectures • 25min

Generative Adversarial Network (GAN)3 lectures • 21min

Requirements

Description

Who this course is for: