1 citations · 1 across the 3 of their papers we have counts for
4 papers
Model compression using knowledge distillation with integrated gradients
David E. Hernandez, Jose Chang, Torbjörn E. M. Nordling
Model compression is critical for deploying deep learning models on resource-constrained devices. We introduce a novel method enhancing knowledge distillation with integrated gradi…
Knowledge Distillation: Enhancing Neural Network Compression with Integrated Gradients
David E. Hernandez, Jose Ramon Chang, Torbjörn E. M. Nordling
Efficient deployment of deep neural networks on resource-constrained devices demands advanced compression techniques that preserve accuracy and interoperability. This paper propose…
An analysis of -invariance and dynamical compensation properties from a control perspective
Akram Ashyani, Yu-Heng Wu, Huan-Wei Hsu +1
Dynamical compensation (DC) provides robustness to parameter fluctuations. As an example, DC enable control of the functional mass of endocrine or neuronal tissue essential for con…
Skin feature point tracking using deep feature encodings
Jose Ramon Chang, Torbjörn E. M. Nordling
Facial feature tracking is a key component of imaging ballistocardiography (BCG) where accurate quantification of the displacement of facial keypoints is needed for good heart rate…