Paper Info
Title
DEFIne: A Fluent Interface DSL for Deep Learning Applications.
Abstract
Recent years have seen a surge of interest in deep learning models that outperform other machine learning algorithms on benchmarks across many disciplines. Most existing deep learning libraries facilitate the development of neural nets by providing a mathematical framework that helps users implement their models more efficiently. This still represents a substantial investment of time and effort, however, when the intention is to compare a range of competing models quickly for a specific task. We present DEFIne, a fluent interface DSL for the specification, optimisation and evaluation of deep learning models. The fluent interface is implemented through method chaining. DEFIne is embedded in Python and is build on top of its most popular deep learning libraries, Keras and Theano. It extends these with common operations for data pre-processing and representation as well as visualisation of datasets and results. We test our framework on three benchmark tasks from different domains: heart disease diagnosis, hand-written digit recognition and weather forecast generation. Results in terms of accuracy, runtime and lines of code show that our DSL achieves equivalent accuracy and runtime to state-of-the-art models, while requiring only about 10 lines of code per application.
Year
DOI
Venue
2017
10.1145/3039895.3039898
RWDSL@CGO
Field
DocType
Citations 
Theano,Programming language,Computer science,Digital subscriber line,Artificial intelligence,Deep learning,Artificial neural network,Fluent interface,Python (programming language),Machine learning,Method chaining,Source lines of code
Conference
0
PageRank 
References 
Authors
0.34
32
2
Name
Order
Citations
PageRank
Nina Dethlefs121120.22
K. A. Hawick229366.26