Book Image

Practical Convolutional Neural Networks

By : Mohit Sewak, Md. Rezaul Karim, Pradeep Pujari
Book Image

Practical Convolutional Neural Networks

By: Mohit Sewak, Md. Rezaul Karim, Pradeep Pujari

Overview of this book

Convolutional Neural Network (CNN) is revolutionizing several application domains such as visual recognition systems, self-driving cars, medical discoveries, innovative eCommerce and more.You will learn to create innovative solutions around image and video analytics to solve complex machine learning and computer vision related problems and implement real-life CNN models. This book starts with an overview of deep neural networkswith the example of image classification and walks you through building your first CNN for human face detector. We will learn to use concepts like transfer learning with CNN, and Auto-Encoders to build very powerful models, even when not much of supervised training data of labeled images is available. Later we build upon the learning achieved to build advanced vision related algorithms for object detection, instance segmentation, generative adversarial networks, image captioning, attention mechanisms for vision, and recurrent models for vision. By the end of this book, you should be ready to implement advanced, effective and efficient CNN models at your professional project or personal initiatives by working on complex image and video datasets.
Table of Contents (11 chapters)

Introducing to autoencoders

An autoencoder is a regular neural network, an unsupervised learning model that takes an input and produces the same input in the output layer. So, there is no associated label in the training data. Generally, an autoencoder consists of two parts:

  • Encoder network
  • Decoder network

It learns all the required features from unlabeled training data, which is known as lower dimensional feature representation. In the following figure, the input data (x) is passed through an encoder that produces a compressed representation of the input data. Mathematically, in the equation, z = h(x), z is a feature vector, and is usually a smaller dimension than x.

Then, we take these produced features from the input data and pass them through a decoder network to reconstruct the original data. 

An encoder can be a fully connected neural network or a&...