Dick Botteldooren

Delayed Memory Unit: Modelling Temporal Dependency Through Delay Gate

2023 · arXiv (Cornell University)

Recurrent Neural Networks (RNNs) are widely recognized for their proficiency in modeling temporal dependencies, making them highly prevalent in sequential data processing applications. Nevertheless, vanilla RNNs are confronted with the well-known issue of gradient vanishing …

BioOSS: A Bio-Inspired Oscillatory State System with Spatio-Temporal Dynamics

2025

Today's deep learning architectures are primarily based on perceptron models, which do not capture the oscillatory dynamics characteristic of biological neurons. Although oscillatory systems have recently gained attention for their closer resemblance to neural behavior, …