IEEE

Adversarial AutoEncoder-Based Large-Scale Dynamic Multiobjective Evolutionary Algorithm

Abstract: Dynamic multiobjective optimization problems (DMOPs) are often scaled to large-scale scenarios in real-world applications, which inevitably must face the triple challenges of massive search ...
IEEE

Contrastive Conditional Adversarial Autoencoder With Class-Specific Forces for Imbalanced Open-Set Fault Detection

Abstract: In real-world industrial scenarios, fault detection faces the widely recognized challenge of data imbalance, which not only refers to the scarcity of fault data but also includes the ...
GitHub

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

In our recent paper, we propose VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech. Several recent end-to-end text-to-speech (TTS) models enabling single ...
EurekAlert!

Molecules imagined using next-generation artificial intelligence validated experimentally

Artificial intelligence learns to 'imagine' novel molecules with the desired properties laying the foundation for AI-powered drug discovery with superhuman abilities Tuesday, September 11th, Rockville ...
Harvard Business School

Detecting Adversarial Attacks via Subset Scanning of Autoencoder Activations and Reconstruction Error

Cintas, Celia, Skyler Speakman, Victor Akinwande, William Ogallo, Komminist Weldemariam, Srihari Sridharan, and Edward McFowland III. "Detecting Adversarial Attacks ...
HotHardware

Facebook Researchers Use AI Trickery To Hide People From Facial Recognition

Artificial intelligence has frequently been used to better identify people and objects. But can AI also be used to mask someone’s identity? Facebook recently announced that it has created video ...