Yalda Mohsenzadeh

OLED: One-Class Learned Encoder-Decoder Network with Adversarial Context\n Masking for Novelty Detection

2021 · arXiv (Cornell University)

Novelty detection is the task of recognizing samples that do not belong to\nthe distribution of the target class. During training, the novelty class is\nabsent, preventing the use of traditional classification approaches. Deep\nautoencoders have been widely …

Improving the adaptive and continuous learning capabilities of artificial neural networks: Lessons from multi-neuromodulatory dynamics

2025 · arXiv (Cornell University)

Continuous, adaptive learning, the ability to adapt to the environment and keep improving performance, is a hallmark of natural intelligence. Biological organisms excel in acquiring, transferring, and retaining knowledge while adapting to volatile environments, making …