|
Connectome-Inspired Adversarial Robustness in Deep Neural Networks
Deep neural networks (DNNs) are artificial neural networks (ANN) and a key component of artificial intelligence (AI) applications. They are designed to function similarly to the human brain and trained using large labeled data sets. There is a plethora of applications for DNNs, including but not limited to driverless cars, security, facial/voice recognition,...
Published: 3/4/2024
|
Inventor(s): Ghulam Rasool, Asim Waqas, Christophe Lenglet, Hamza Farooq
Keywords(s): Artificial Intelligence, Neural Networks, Security, Software
Category(s): Software, Engineering > Electronics
|
|
A New Risk Management Tool for Medical Imaging Software
Deep neural networks (DNNs) help radiologists locate, characterize, and segment tumors. These software tools augment imagery in regions that are otherwise obscured by signal noise or streaks. DNNs reduce imaging session times and thereby reduce radiation exposure. On the other hand, “black box” DNNs defy clinical scrutiny, make patient consultations...
Published: 2/15/2024
|
Inventor(s): Nidhal Bouaynaya, Ghulam Rasool, Dimah Dera
Keywords(s): Artificial Intelligence, MRI, Neural Networks, Safety
Category(s): Software
|
