Search Results - omead+pooladzandi

1 Results Sort By:
Artificial Neural Network Train-Time Poison Defense via Energy-Based Model Dynamics Sampling (Case No. 2024-199)
Summary: UCLA researchers in the Department of Electrical and Computer Engineering have developed a novel preprocessing algorithm to purify imperceptibly poisoned training datasets that may lead to misclassification and maintain image quality. Background: Large datasets are important for the effectiveness of machine learning models, serving as the...
Published: 9/30/2024   |   Inventor(s): Gregory Pottie, Omead Pooladzandi, Sunay Bhat, Jeffrey Jiang
Keywords(s): AI algorithms, Algorithm, Artificial Intelligence, artificial intelligence augmentation, Automation, Autonomous driving, Big Data, Computer Aided Learning, Data Corruption, Digital Health, Machine Learning, Machine Learning Autonomous Car Gradient Descent
Category(s): Software & Algorithms, Platforms > Diagnostic Platform Technologies, Therapeutics > Radiology, Medical Devices > Monitoring And Recording Systems, Medical Devices > Neural Stimulation, Mechanical > Sensors