Convolutional neural networks use the data that is represented in images to learn. In this chapter, we will probe data in images, and we will learn how to use Keras to train a neural network to classify objects that appear in images. 

Introducing convolutional neural networks

Images as data: visualizations

Images as data: changing images

Classifying images

Using one-hot encoding to represent images

Evaluating a classifier

Classification with Keras

Build a neural network

Compile a neural network

Fitting a neural network model to clothing data

Cross-validation for neural network evaluation

Image Processing With Neural Networks

Convolutions are the fundamental building blocks of convolutional neural networks. In this chapter, you will be introducted to convolutions and learn how they operate on image data. You will also see how you incorporate convolutions into Keras neural networks. 

Convolutions

One dimensional convolutions

Image convolutions

Defining image convolution kernels

Implementing image convolutions in Keras

Convolutional network for image classification

Training a CNN to classify clothing types

Evaluating a CNN with test data

Tweaking your convolutions

Add padding to a CNN

Add strides to a convolutional network

Calculate the size of convolutional layer output

Using Convolutions

Convolutional neural networks gain a lot of power when they are constructed with multiple layers (deep networks). In this chapter, you will learn how to stack multiple convolutional layers into a deep network. You will also learn how to keep track of the number of parameters, as the network grows, and how to control this number.

Going deeper

Creating a deep learning network

Train a deep CNN to classify clothing images

What is special about a deep network?

How many parameters?

How many parameters in a CNN?

How many parameters in a deep CNN?

Pooling operations

Write your own pooling operation

Keras pooling layers

Train a deep CNN with pooling to classify images

Going Deeper

There are many ways to improve training by neural networks. In this chapter, we will focus on our ability to track how well a network is doing, and explore approaches towards improving convolutional neural networks.

Tracking learning

Plot the learning curves

Using stored weights to predict in a test set

Regularization

Adding dropout to your network

Add batch normalization to your network

Interpreting the model

Extracting a kernel from a trained network

Shape of the weights

Visualizing kernel responses

Next steps

Understanding and Improving Deep Convolutional Networks

Image modeling often requires deep learning methods that use data to train neural network algorithms for various machine learning tasks. Convolutional neural networks (CNNs) are particularly powerful neural networks that you'll use to classify different types of objects for the analysis of images. This four-hour course will teach you how to construct, train, and evaluate CNNs using Keras.

<h2>Learn to Use Convolutional Neural Networks in Python</h2>
  Image model often requires deep learning methods that use data to train neural
  network algorithms to do various machine learning tasks. Convolutional neural
  networks (CNNs) are particularly powerful neural networks that you'll use to
  classify different types of objects for the analysis of images. This four-hour
  course will teach you how to construct, train, and evaluate CNNs using Keras.
  <br><br>
  Turning images into data and teaching neural networks to classify them is a
  challenging element of deep learning with extensive applications throughout
  business and research, from helping an eCommerce site manage inventory more
  easily to allowing cancer researchers to quickly spot dangerous melanoma.
  <br><br>
  <h2>Discover Keras CNNs</h2>
  The first chapter of this course covers how images can be seen as data, and
  how you can use Keras to train a neural network to classify objects found in
  images.
  <br><br>
  The second chapter will cover convolutions, a fundamental part of CNNs. You’ll
  learn how they operate on image data and learn how to train and tweak your
  Keras CNN using test data. Later chapters go into more detail and teach you
  how to create a deep learning network.
  <br><br>
  <h2>Build Your Own Keras Neural Network</h2>
  You’ll end the course by learning the different ways that you can track how
  well a CNN is doing and how you can improve their performance. At this point,
  you’ll be able to build Keras neural networks, optimize them, and visualize
  their responses across a range of applications.

Introduction to Deep Learning with Keras

Learn to use deep learning to analyze image data using Keras with Python by constructing, training, and evaluating convolutional neural networks. 

Image Processing with Keras in Python

Learn to conduct image analysis using Keras with Python by constructing, training, and evaluating convolutional neural networks. 

Image Modeling with Keras

Elaborazione delle immagini in Python

Fondamenti di Keras

Senior Data Scientist, University of Washington

Wrapping up

What did we learn?

Model interpretation

Road

What next?

Residual networks

Fully convolutional networks

Generative adversarial networks

Good luck!

https://s3.amazonaws.com/assets.datacamp.com/production/course_7823/subtitles/course_7823_74a6f1f7d64946e4fd00d0da02be339e.vtt

Understanding and Improving Deep Convolutional Networks - Next steps

Next steps

Create Your Free Account