معرفی
Gü cin Baykal Can serves as a Research Fellow within the Department of Mathematics and Computer Science at the University of Southern Denmark. Her academic work centers on data science with specialized focus on advanced deep learning architectures and generative modeling techniques.
Her research spans Deep Learning, Variational Autoencoders, and Generative Models as core specialties, extending to Machine Learning, Artificial Intelligence, and Computer Science. She develops novel methodologies to overcome critical challenges like codebook collapse in discrete variational autoencoders, significantly advancing unsupervised representation learning systems and neural network efficiency.
Her publication profile features a 2024 Pattern Recognition article introducing EdVAE, an evidential discrete variational autoencoder framework. This work exemplifies her contributions to Computer Science and Artificial Intelligence, particularly in Neural Networks, Representation Learning, and Unsupervised Learning domains, demonstrating technical innovation in generative model stability.
No scientific awards or honors were documented in the available information.
There is no available information regarding graduate student supervision, research grant funding, or academic advising activities.
Details about laboratory affiliations, research team memberships, or collaborative projects were not specified in the source material.
