Faculty: Gal Mishne, Ph.D. Abstract: Understanding why and how certain neural networks outperform others is key to guiding future development of network architectures and optimization methods. To this end, we introduce a novel visualization al..
Faculty: Armin Schwartzman, Ph.D. The expected Euler characteristic (EEC) curve of excursion sets of a Gaussian random field is used to approximate the distribution of its supremum for high thresholds. Viewed as a function of the excursion thr..
Faculty: Alexander Cloninger, Ph.D. Abstract— Stochastic-sampling-based Generative Neural Networks, such as Restricted Boltzmann Machines and Generative Adversarial Networks, are now used for applications such as denoising, image occlusion r..