English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep Learning (DL) is one of the hottest trends in machine learning as DLapproaches produced results superior to the state-of-the-art in problematicareas such as image processing and natural language processing (NLP). To fosterthe growth of DL, several open source frameworks appeared providingimplementations of the most common DL algorithms. These frameworks vary in thealgorithms they support and in the quality of their implementations. Thepurpose of this work is to provide a qualitative and quantitative comparisonamong three of the most popular and most comprehensive DL frameworks (namelyGoogle's TensorFlow, University of Montreal's Theano and Microsoft's CNTK). Theultimate goal of this work is to help end users make an informed decision aboutthe best DL framework that suits their needs and resources. To ensure that ourstudy is as comprehensive as possible, we conduct several experiments usingmultiple benchmark datasets from different fields (image processing, NLP, etc.)and measure the performance of the frameworks' implementations of different DLalgorithms. For most of our experiments, we find out that CNTK'simplementations are superior to the other ones under consideration.

A detailed comparative study of open source deep learning frameworks