Search icon CANCEL
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Deep Learning with TensorFlow

You're reading from   Deep Learning with TensorFlow Explore neural networks and build intelligent systems with Python

Arrow left icon
Product type Paperback
Published in Mar 2018
Publisher Packt
ISBN-13 9781788831109
Length 484 pages
Edition 2nd Edition
Languages
Arrow right icon
Authors (2):
Arrow left icon
Giancarlo Zaccone Giancarlo Zaccone
Author Profile Icon Giancarlo Zaccone
Giancarlo Zaccone
Md. Rezaul Karim Md. Rezaul Karim
Author Profile Icon Md. Rezaul Karim
Md. Rezaul Karim
Arrow right icon
View More author details
Toc

Table of Contents (13) Chapters Close

Preface 1. Getting Started with Deep Learning FREE CHAPTER 2. A First Look at TensorFlow 3. Feed-Forward Neural Networks with TensorFlow 4. Convolutional Neural Networks 5. Optimizing TensorFlow Autoencoders 6. Recurrent Neural Networks 7. Heterogeneous and Distributed Computing 8. Advanced TensorFlow Programming 9. Recommendation Systems Using Factorization Machines 10. Reinforcement Learning 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:

LeNet5

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...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $19.99/month. Cancel anytime