TY - GEN
T1 - SOFTWARE FRAMEWORKS FOR ARTIFICIAL INTELLIGENCE: COMPARSION OF LOW-LEVEL AND HIGH-LEVEL APPROACHES
AU - Bogner, Michael
AU - Weindl, Florian
AU - Wiesinger, Franz Leopold
PY - 2019
Y1 - 2019
N2 - As nearly every artificial intelligence application is based on a framework, using the best fitting one for the task is key in developing an efficient solution quickly. Since there are two main types of frameworks, based on low and high abstraction level approaches, these two types will get compared and evaluated throughout this paper using Tensorflow and Keras as representatives. Key features of artificial intelligence frameworks for industrial applications are performance, expandability, abstraction level and therefore ease of use for rapid prototyping. All those features are major factors to keep development time and costs as low as possible, while maximizing product quality. To evaluate both approaches by these criteria a neural network classifying handwritten digits is implemented.
AB - As nearly every artificial intelligence application is based on a framework, using the best fitting one for the task is key in developing an efficient solution quickly. Since there are two main types of frameworks, based on low and high abstraction level approaches, these two types will get compared and evaluated throughout this paper using Tensorflow and Keras as representatives. Key features of artificial intelligence frameworks for industrial applications are performance, expandability, abstraction level and therefore ease of use for rapid prototyping. All those features are major factors to keep development time and costs as low as possible, while maximizing product quality. To evaluate both approaches by these criteria a neural network classifying handwritten digits is implemented.
KW - Evaluation
KW - Keras
KW - Neural network
KW - Tensorflow
UR - http://www.scopus.com/inward/record.url?scp=85073784051&partnerID=8YFLogxK
U2 - 10.46354/i3m.2019.emss.016
DO - 10.46354/i3m.2019.emss.016
M3 - Conference contribution
T3 - 31st European Modeling and Simulation Symposium, EMSS 2019
SP - 96
EP - 102
BT - 31st European Modeling and Simulation Symposium, EMSS 2019
A2 - Affenzeller, Michael
A2 - Bruzzone, Agostino G.
A2 - Longo, Francesco
A2 - Pereira, Guilherme
T2 - Proceedings of the 31st European Modeling and Simulation Symposium EMSS2019
Y2 - 17 September 2019 through 20 September 2019
ER -