You're reading from Neural Networks with R Build smart systems by implementing popular deep learning models in R

Product type Paperback

Published in Sep 2017

Publisher Packt

ISBN-13 9781788397872

Length 270 pages

Edition 1st Edition

Languages

Concepts

Deep Learning

Authors (2):

Balaji Venkateswaran

Giuseppe Ciaburro

View More author details

Table of Contents (8) Chapters

Preface

1. Neural Network and Artificial Intelligence Concepts

2. Learning Process in Neural Networks FREE CHAPTER

3. Deep Learning Using Multilayer Neural Networks

4. Perceptron Neural Network Modeling – Basic Models

5. Training and Visualizing a Neural Network in R

6. Recurrent and Convolutional Neural Networks

7. Use Cases of Neural Networks – Advanced Topics

Recurrent Neural Network

Within the set of Artificial Neural Networks (ANN), there are several variants based on the number of hidden layers and data flow. One of the variants is RNN, where the connections between neurons can form a cycle. Unlike feed-forward networks, RNNs can use internal memory for their processing. RNNs are a class of ANNs that feature connections between hidden layers that are propagated through time in order to learn sequences. RNN use cases include the following fields:

Stock market predictions
Image captioning
Weather forecast
Time-series-based forecasts
Language translation
Speech recognition
Handwriting recognition
Audio or video processing
Robotics action sequencing

The networks we have studied so far (feed-forward networks) are based on input data that is powered to the network and converted into output. If it is a supervised learning algorithm,...

The rest of the chapter is locked

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

Start free trial

Renews at $19.99/month. Cancel anytime

Authors (2)

Balaji Venkateswaran

Balaji Venkateswaran is an AI expert, data scientist, machine learning practitioner, and database architect. He has 17+ years of experience in investment banking payment processing, telecom billing, and project management. He has worked for major companies such as ADP, Goldman Sachs, MasterCard, and Wipro. Balaji is a trainer in data science, Hadoop, and Tableau. He holds a postgraduate degree PG in business analytics from Great Lakes Institute of Management, Chennai. Balaji has expertise relating to statistics, classification, regression, pattern recognition, time series forecasting, and unstructured data analysis using text mining procedures. His main interests are neural networks and deep learning. Balaji holds various certifications in IBM SPSS, IBM Watson, IBM big data architect, cloud architect, CEH, Splunk, Salesforce, Agile CSM, and AWS. If you have any questions, don't hesitate to message him on LinkedIn (balvenkateswaran); he will be more than glad to help fellow data scientists.

See other products by Balaji Venkateswaran

Giuseppe Ciaburro

Giuseppe Ciaburro holds a PhD and two master's degrees. He works at the Built Environment Control Laboratory - Università degli Studi della Campania "Luigi Vanvitelli". He has over 25 years of work experience in programming, first in the field of combustion and then in acoustics and noise control. His core programming knowledge is in MATLAB, Python and R. As an expert in AI applications to acoustics and noise control problems, Giuseppe has wide experience in researching and teaching. He has several publications to his credit: monographs, scientific journals, and thematic conferences. He was recently included in the world's top 2% scientists list by Stanford University (2022).

See other products by Giuseppe Ciaburro