Analytics Insight

Self-Learning AI Models That Don’t Need Retraining

Self-learning AI models can improve after deployment without full retraining by using context, memory, and feedback instead ...
IEEE

ADC: Adversarial attacks against object Detection that evade Context consistency checks

Abstract: Deep Neural Networks (DNNs) have been shown to be vulnerable to adversarial examples, which are slightly perturbed input images which lead DNNs to make wrong predictions. To protect from ...