RésuméConvolutional neural networks (CNNs) are widely used for diverse tasks, such as image recognition and analysis. Recently, research aimed at finding CNN architectures that can be used in various contexts/applications and provide the latest performance has yielded fruitful results, resulting in numerous recommendation models tailored for more or less specific purposes. Finding the right CNN is a challenging issue: there are many possible architectures, hyperparameters, and frameworks that can be considered. From a software engineering perspective, having such diversity can be difficult to deal with when trying to maintain a system or trying to reason effectively (for example, consider choosing the best solution for deployment on a system with high potential impact on daily life). In this master thesis, we investigate how variability can be expressed to derive different CNN variants. We develop a generator on top of Keras for deriving variants of LeNet, ResNet, and DenseNet architectures. Our results show that we can reach accurate results on MNIST and CIFAR-10. The next step of our work is to improve the generator for other architectures (e.g. Xception, SqueezeNet,...) and find optimal ways to explore the configuration space.
Mots-clés / Keywords
|la date de réponse||22 juin 2021|
|Superviseur||Gilles Perrouin (Promoteur), Benoît Frénay (Copromoteur) & Paul Temple (Copromoteur)|