In this chapter, we will use convolutional neural networks (CNNs) to create a classifier that can predict whether a given image contains a cat or a dog.
This project marks the first in a series of projects where we will use neural networks for image recognition and computer vision problems. As we shall see, neural networks have proven to be an extremely effective tool for solving problems in computer vision.
In this chapter, we will cover the following topics:
- Motivation for the problem that we're trying to tackle: image recognition
- Neural networks and deep learning for computer vision
- Understanding convolution and max pooling
- Architecture of CNNs
- Training CNNs in Keras
- Using transfer learning to leverage on a state-of-the art neural network
- Analysis of our results
