Search Results - christopher+wiedeman

3 Results Sort By:
Decorrelation Mechanism and Dual Neck Autoencoders for Deep Learning
RPI ID: 2022-018-201 Innovation Summary: A dual-neck autoencoder architecture is introduced to improve feature separation and reduce redundancy in deep learning models. The decorrelation mechanism embedded in the encoder layers enhances generalization by minimizing overlap in learned representations. This design allows for more effective training in...
Published: 3/10/2026   |   Inventor(s): Christopher Wiedeman, Ge Wang
Keywords(s): Adversarial Attacks, Attack Transferability, computer vision, Decorrelation, deep learning
Category(s): Computational Science and Engineering
Machine Learning for Individual Moral Decision Making
RPI ID: 2020-045-401 Innovation Summary: A machine learning framework is developed to model and predict individual moral decision-making behavior. The system uses behavioral data and contextual inputs to train personalized models that reflect ethical preferences. It supports applications in autonomous systems, education, and behavioral research. The...
Published: 3/10/2026   |   Inventor(s): Christopher Wiedeman, Uwe Kruger, Ge Wang
Keywords(s): AI, Artificial Intelligence, deep learning, ethics, Moral Machine experiment
Category(s): Biotechnology and the Life Sciences
Cold Therapy Dynamic Hand Splint
Muscle spasticity, which affects over 12 million people world-wide, is a chronic condition in which some muscles are constantly activated, leaving joints immobile. Prolonged contraction can lead to the development of contractures, permanent shortening of muscles and tendons, which often requires surgical treatments. Furthermore, muscle spasticity greatly...
Published: 2/26/2026   |   Inventor(s): Brandon Dorr, Cole Hunter, Christopher Wiedeman, Jeffrey Kleim, Mary "Kay" Wing
Keywords(s):  
Category(s): Life Science (All LS Techs), Medical Devices, Neurodegenerative Disease Technologies