swMATH ID: 38609
Software Authors: Baptiste Wicht, Jean Hennebert, Andreas Fischer
Description: DLL: A Blazing Fast Deep Neural Network Library. Deep Learning Library (DLL) is a new library for machine learning with deep neural networks that focuses on speed. It supports feed-forward neural networks such as fully-connected Artificial Neural Networks (ANNs) and Convolutional Neural Networks (CNNs). It also has very comprehensive support for Restricted Boltzmann Machines (RBMs) and Convolutional RBMs. Our main motivation for this work was to propose and evaluate novel software engineering strategies with potential to accelerate runtime for training and inference. Such strategies are mostly independent of the underlying deep learning algorithms. On three different datasets and for four different neural network models, we compared DLL to five popular deep learning frameworks. Experimentally, it is shown that the proposed framework is systematically and significantly faster on CPU and GPU. In terms of classification performance, similar accuracies as the other frameworks are reported.
Homepage: https://arxiv.org/abs/1804.04512
Related Software: PRMLT; Fizzy; Lingvo; Kpax3; pyGCluster; GmmFlow.jl; EmpiriciSN; LIBSVM.jl; BSMac; Jlnv; GCNv2; TensorFlow.jl; Metalhead.jl; ImageProjectiveGeometry.jl; LightNLP.jl; BAMSE; AlexNet; MultivariateStats.jl; CUDA.jl; NearestNeighbors.jl
Referenced in: 1 Publication

Referenced in 1 Serial

1 Computer Science Review

Referenced in 1 Field

1 Computer science (68-XX)

Referencing Publications by Year