Reservoir computing (RC), first applied to temporal signal processing, is a recurrent neural
network in which neurons are randomly connected. Once initialized, the connection …

Abstract Machine learning has become indispensable across various domains, yet
understanding its theoretical underpinnings remains challenging for many practitioners and …

Continuous time recurrent neural networks (CTRNNs) are systems of coupled ordinary
differential equations (ODEs) inspired by the structure of neural networks in the brain …

Recurrent Neural Networks (RNNs) are widely used for sequential processing but face
fundamental limitations with continual inference due to state saturation, requiring disruptive …

Recent interest in the 'Large Language Models' of deep learning has led to widespread
conjecture that artificial general intelligence (AGI) is thereby imminent. At the other end of …

While machine learning (ML) gives rise to astonishing results in automated systems, it is
usually at the cost of large data requirements. This makes many successful algorithms from …

This thesis being the preliminary culmination of my academic journey, I feel it appropriate to
thank a number of people who have been a positive influence along the way. First and …