Exploring Deep Learning for Search
With chapters selected by Tommaso Teofili
  • February 2020
  • ISBN 9781617297830
  • 126 pages
In Exploring Deep Learning for Search, author and deep learning guru Tommaso Teofili features three chapters from his book, Deep Learning for Search. Inside, you’ll see how neural search saves you time and improves search effectiveness by automating work that was previously done manually. You’ll also explore how to widen your search net by using a recurrent neural network (RNN) to add text-generation functionality to a search engine. In the final chapter, you’ll delve into using convolutional neural networks (CNNs) to index images and make them searchable by their content. With this laser-focused guide, you’ll have an excellent grasp on the basics of improving search with deep learning.

About the Technology

Giving users relevant search results is a challenge, especially when search terms are imprecise, data is poorly indexed, or images have minimal metadata. But neural networks and deep learning techniques can empower your search engines to return high quality results from even the sloppiest query! Even better, the more you use your search engines, the more they learn, providing better search results all the time!
Table of Contents detailed table of contents

Part 1 from Deep Learning for Search by Tommaso Teofili

Neural search

Neural networks and deep learning

What is machine learning?

A roadmap for learning deep learning

Retrieving useful information

Text, tokens, terms, and search fundamentals

Relevance first

Classic retrieval models

Precision and recall

Unsolved problems

Opening the search engine black box

Deep learning to the rescue

Index, please meet neuron

Neural network training

Part 2 from Deep Learning for Search by Tommaso Teofili

From plain retrieval to text generation

Information need vs. query: Bridging the gap

Generating alternative queries

Data preparation

Wrap-up of generating data

Learning over sequences

Recurrent neural networks

RNN internals and dynamics

Long-term dependencies

Long short-term memory networks

LSTM networks for unsupervised text generation

Unsupervised query expansion

From unsupervised to supervised text generation

Sequence-to-sequence modeling

Considerations for production systems

Part 3 from Deep Learning for Search by Tommaso Teofili

Content-based image search

A look back: Text-based image retrieval

Understanding images

Image representations

Feature extraction

Deep learning for image representation

Convolutional neural networks

Locality-sensitive hashing

Working with unlabeled images

What's inside

  • Chapter 1, “Neural search”
  • Chapter 3, “From plain retrieval to text generation”
  • Chapter 8, “Content-based image search”

About the author

Tommaso Teofili is a software engineer with a passion for open source and machine learning. As a member of the Apache Software Foundation, he contributes to a number of open source projects, ranging from topics like information retrieval (such as Lucene and Solr) to natural language processing and machine translation (including OpenNLP, Joshua, and UIMA).

He currently works at Adobe, developing search and indexing infrastructure components, and researching the areas of natural language processing, information retrieval, and deep learning. He has presented search and machine learning talks at conferences including BerlinBuzzwords, International Conference on Computational Science, ApacheCon, EclipseCon, and others. You can find him on Twitter at @tteofili.

placing your order...

Don't refresh or navigate away from the page.
eBook $0.00 PDF only + liveBook
Exploring Deep Learning for Search (eBook) added to cart
continue shopping
go to cart

Prices displayed in rupees will be charged in USD when you check out.

FREE domestic shipping on three or more pBooks