Researchers suggest that complex numbers can protect AI based algorithms from taking a wrong turn in decision making processes. Artificial intelligence (AI) models are used in a variety of applications such as cognitive manufacturing, safety devices, identification, etc. But the algorithm can be easily manipulated or fooled through adversarial attacks. These attacks break the AI’s […]
The post Imaginary Numbers Protect AI From Adversarial Attacks appeared first on Electronics For You.
View more at https://www.electronicsforu.com/tech-zone/security-and-id-tech/imaginary-numbers-protect-ai-from-adversarial-attacks.
Credit- EFY. Published by Department of EEE, ADBU: tinyurl.com/eee-adbu
