Description

In this self-paced course, you will learn how to use TensorFlow 2 to build convolutional neural networks (CNNs). You will learn how to apply CNNs to several practical image recognition datasets and learn about techniques that help improve performance, such as batch normalization, data augmentation, and transfer learning.

TensorFlow is the world's most popular library for deep learning, and it is built by Google. It is the library of choice for many companies doing AI (Artificial Intelligence) and machine learning. So, if you want to do deep learning, you must know TensorFlow. In this course, you will learn how to use TensorFlow 2 to build convolutional neural networks (CNN). We will first start by having an in-depth look at what convolution is, why it is useful, and how to integrate it into a neural network. Then you will learn how to apply CNNs to several practical image recognition datasets, from small and relatively simple to large and complex. Next, you will learn how to perform text preprocessing and text classification with CNNs. In the last section, you will learn about techniques that help improve performance, such as batch normalization, data augmentation, and transfer learning for Computer Vision. By the end of this course, we will have understood how to build convolutional neural networks in deep learning with TensorFlow.

What You Will Learn

Understand the concept of convolution
Integrate convolution into neural networks
Apply CNNs to several image recognition datasets, both small and large
Learn best practices for designing CNN architectures
Learn about batch normalization and data augmentation
Learn how to preform text preprocessing

Audience

This course is designed for anyone interested in deep learning and machine learning or for anyone who wants to implement convolutional neural networks in TensorFlow 2.

One must have decent Python programming skills, should know how to build a feedforward ANN (Artificial Neural Network) in TensorFlow 2, and must have experience with data science libraries such as NumPy and Matplotlib.

Approach

In this self-paced course, you will learn how to use TensorFlow 2 to build convolutional neural networks. The course is well-balanced with theory that explains the CNN concepts and hands-on coding exercises for practical understanding.

Key Features

Learn how to use TensorFlow 2 to build Convolutional Neural Networks (CNNs) * The course covers Natural Language Processing (NLP) and transfer learning for Computer Vision * Explains how to apply CNNs to NLP

About the Author

Lazy Programmer

The Lazy Programmer, a distinguished online educator, boasts dual master's degrees in computer engineering and statistics, with a decade-long specialization in machine learning, pattern recognition, and deep learning, where he authored pioneering courses. His professional journey includes enhancing online advertising and digital media, notably increasing click-through rates and revenue. As a versatile full-stack software engineer, he excels in Python, Ruby on Rails, C++, and more. His expansive knowledge covers areas like bioinformatics and algorithmic trading, showcasing his diverse skill set. Dedicated to simplifying complex topics, he stands as a pivotal figure in online education, adeptly navigating students through the nuances of data science and AI.

Course Outline

1. Welcome

1. Introduction

In this video, we will introduce the author and understand the course learning objective.

2. Outline

In this video, we will understand the course learning approach and what is required to start with this course. Then we will also understand what is covered in this course.

2. Convolutional Neural Networks (CNNs)

1. What Is Convolution? (Part 1)

In this video, we will get introduced to the concept of convolution.

2. What Is Convolution? (Part 2)

In this video, we will look at a new perspective on convolution to understand how it works.

3. What Is Convolution? (Part 3)

In this video, you will learn how to view convolution as matrix multiplication.

4. Convolution on Color Images

In this video, we will understand convolution on color images.

5. CNN Architecture

In this video, we will understand the CNN architecture.

6. CNN Code Preparation

In this video, we will look at the code preparation we will use for CNN and understand it.

7. CNN for Fashion MNIST

In this video, we will start with implementing CNN with the fashion MNIST dataset.

8. CNN for CIFAR-10

In this video, we will work on image classification with the CIFAR-10 dataset.

9. Data Augmentation

In this video, you will learn about data augmentation.

10. Batch Normalization

In this video, you will learn about batch normalization.

11. Improving CIFAR-10 Results

In this video, you will learn how to improve CIFAR-10 results using data augmentation and batch normalization.

12. Suggestion Box

In this video, we will look at the suggestion box where we can add feedback for this course.

3. Natural Language Processing (NLP)

1. Embeddings

In this video, we will understand the text as sequence data.

2. Code Preparation (NLP)

In this video, we will look at the code preparation we will use for NLP and understand it.

3. Text Preprocessing

In this video, we will move into action and understand how to do text preprocessing using Colab notebook.

4. CNNs for Text

In this video, we will understand how we can use CNNs for text sequences.

5. Text Classification with CNNs

In this video, we will move into action and work on text classification with CNNs.

4. Transfer Learning for Computer Vision

1. Transfer Learning Theory

In this video, we will get introduced to the concept of transfer learning.

2. Some Pre-Trained Models (VGG, ResNet, Inception, MobileNet)

In this video, we will understand VGG, ResNet, Inception, and MobileNet.

3. Large Datasets and Data Generators

In this video, you will learn how to work with large image datasets in TensorFlow and Keras with data generators.

4. 2 Approaches to Transfer Learning

In this video, we will discuss the two approaches used for transfer learning, which we will use in the next videos.

5. Transfer Learning Code (Part 1)

In this video, we will dive into action and look at codes for transfer learning with data augmentation.

6. Transfer Learning Code (Part 2)

In this video, we will dive into action and look at codes for transfer learning without data augmentation.

Course Images

Deep Learning - Convolutional Neural Networks with TensorFlow

By Packt

Booking options

Highlights