Automated and Disciplined ConvNet Architecture Exploration

Défense de mémoire de Gratia Antoine

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 - isabelle.daelman@unamur.be
Télecharger : vCal