no code implementations • 1 Aug 2023 • Stephan Johann Lehmler, Muhammad Saif-ur-Rehman, Tobias Glasmachers, Ioannis Iossifidis
Our approach models activation patterns of thresholded nodes in (deep) artificial neural networks as stochastic processes.
no code implementations • 30 Dec 2021 • Stephan Johann Lehmler, Muhammad Saif-ur-Rehman, Tobias Glasmachers, Ioannis Iossifidis
In this study, we investigate the effectiveness of transfer learning using weight initialization for recalibration of two different pretrained deep learning models on a new subjects data, and compare their performance to subject-specific models.