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
Keras 2.x Projects

You're reading from   Keras 2.x Projects 9 projects demonstrating faster experimentation of neural network and deep learning applications using Keras

Arrow left icon
Product type Paperback
Published in Dec 2018
Publisher Packt
ISBN-13 9781789536645
Length 394 pages
Edition 1st Edition
Languages
Tools
Arrow right icon
Author (1):
Arrow left icon
Giuseppe Ciaburro Giuseppe Ciaburro
Author Profile Icon Giuseppe Ciaburro
Giuseppe Ciaburro
Arrow right icon
View More author details
Toc

Table of Contents (13) Chapters Close

Preface 1. Getting Started with Keras FREE CHAPTER 2. Modeling Real Estate Using Regression Analysis 3. Heart Disease Classification with Neural Networks 4. Concrete Quality Prediction Using Deep Neural Networks 5. Fashion Article Recognition Using Convolutional Neural Networks 6. Movie Reviews Sentiment Analysis Using Recurrent Neural Networks 7. Stock Volatility Forecasting Using Long Short-Term Memory 8. Reconstruction of Handwritten Digit Images Using Autoencoders 9. Robot Control System Using Deep Reinforcement Learning 10. Reuters Newswire Topics Classifier in Keras 11. What is Next? 12. Other Books You May Enjoy

Fashion Article Recognition Using Convolutional Neural Networks

Object recognition is the ability to find a specific object in a sequence of images or videos. This task is performed automatically by human beings, even in particularly complex scenarios. For machines, it represents the challenges of the future. In convolutional neural networks, the fields of different neurons are partially overlapped so that they cover the entire field of view altogether. The response of a single neuron to stimuli taking place in its receptive field can be mathematically approximated by a convolution operation. A CNN is a particular type of ANN, which used above all other models for the analysis of images and the application of graphic filters. CNNs eliminate the need for the manual extraction of features, as these are learned directly from CNN. They produce state-of-the-art recognition results...

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 £16.99/month. Cancel anytime