Book Image

Deep Learning with TensorFlow - Second Edition

By : Giancarlo Zaccone, Md. Rezaul Karim
Book Image

Deep Learning with TensorFlow - Second Edition

By: Giancarlo Zaccone, Md. Rezaul Karim

Overview of this book

Deep learning is a branch of machine learning algorithms based on learning multiple levels of abstraction. Neural networks, which are at the core of deep learning, are being used in predictive analytics, computer vision, natural language processing, time series forecasting, and to perform a myriad of other complex tasks. This book is conceived for developers, data analysts, machine learning practitioners and deep learning enthusiasts who want to build powerful, robust, and accurate predictive models with the power of TensorFlow, combined with other open source Python libraries. Throughout the book, you’ll learn how to develop deep learning applications for machine learning systems using Feedforward Neural Networks, Convolutional Neural Networks, Recurrent Neural Networks, Autoencoders, and Factorization Machines. Discover how to attain deep learning programming on GPU in a distributed way. You'll come away with an in-depth knowledge of machine learning techniques and the skills to apply them to real-world projects.
Table of Contents (15 chapters)
Deep Learning with TensorFlow - Second Edition
Contributors
Preface
Other Books You May Enjoy
Index

LeNet5


The LeNet5 CNN architecture was invented by Yann LeCun in 1998 and was the first CNN. It is a multilayered feed-forward network specifically designed to classify handwritten digits. It was used in LeCun's experiments and consists of seven layers containing trainable weights. The LeNet5 architecture looks like this:

Figure 6: The LeNet5 network

The LeNet5 architecture consists of three convolutional layers and two alternating sequence pooling layers. The last two layers correspond to a traditional fully connected neural network, that is, a fully connected layer followed by an output layer. The main function of the output layer is to calculate the Euclidean distance between the input vector and the parameter vector. The output functions identify the difference between the measurements of the input pattern and our model. The output is kept minimal in order to achieve the best model. Therefore, the fully connected layer is configured so that the difference between the measurements of the...