Accueil UNamur > Agenda > Automated and Disciplined ConvNet Architecture Exploration

Automated and Disciplined ConvNet Architecture Exploration

Défense de mémoire de Gratia Antoine

Catégorie : mémoire
Date : 22/06/2021 15:00 - 22/06/2021 16:00
Lieu : A distance par teams
Orateur(s) : Antoine Gratia
Organisateur(s) : Isabelle Daelman

Via ce lien

Convolutional neural networks (CNNs) are widely used for diverse tasks, such as image recognition and analysis.  Recently, research aimed at fi            CNN archi- tectures 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, hav- ing such diversity can be diffi     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 diff t 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 fi optimal ways to explore the configuration space

Contact : Isabelle Daelman -
Télecharger : vCal