A Comprehensive Classification of Deep Learning Libraries

Hari Pandey, David Windridge

Research output: Chapter in Book/Report/Conference proceedingConference proceeding (ISBN)peer-review

181 Downloads (Pure)


Deep learning (DL) networks are composed of multiple processing layers that learn data representations with multiple levels of abstraction. In recent years, DL networks have significantly improved the state of the art across different domains, including speech processing, text mining, pattern recognition, object detection, robotics, and big data analytics. Generally, a researcher or practitioner who is planning to use DL networks for the first time faces difficulties in selecting suitable software tools. The present article provides a comprehensive list and taxonomy of current programming languages and software tools that can be utilized for implementation of DL networks. The motivation of this article is hence to create awareness among researchers, especially beginners, regarding the various languages and interfaces that are available to implement deep learning and to provide a simplified ontological basis for selecting between them.
Original languageEnglish
Title of host publicationAdvances in Intelligent Systems and Computing
PublisherSpringer, Singapore
ISBN (Print)978-981-13-1164-2
Publication statusE-pub ahead of print - 29 Sept 2018


Dive into the research topics of 'A Comprehensive Classification of Deep Learning Libraries'. Together they form a unique fingerprint.

Cite this