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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In recent years, Deep Learning (DL) has found great success in domains suchas multimedia understanding. However, the complex nature of multimedia datamakes it difficult to develop DL-based software. The state-of-the art tools,such as Caffe, TensorFlow, Torch7, and CNTK, while are successful in theirapplicable domains, are programming libraries with fixed user interface,internal representation, and execution environment. This makes it difficult toimplement portable and customized DL applications.  In this paper, we present DeepDSL, a domain specific language (DSL) embeddedin Scala, that compiles deep networks written in DeepDSL to Java source code.Deep DSL provides (1) intuitive constructs to support compact encoding of deepnetworks; (2) symbolic gradient derivation of the networks; (3) static analysisfor memory consumption and error detection; and (4) DSL-level optimization toimprove memory and runtime efficiency.  DeepDSL programs are compiled into compact, efficient, customizable, andportable Java source code, which operates the CUDA and CUDNN interfaces runningon Nvidia GPU via a Java Native Interface (JNI) library. We evaluated DeepDSLwith a number of popular DL networks. Our experiments show that the compiledprograms have very competitive runtime performance and memory efficiencycompared to the existing libraries.

DeepDSL: A Compilation-based Domain-Specific Language for Deep Learning