This research develops advanced brain-machine interface systems to improve life for spinal cord injury patients. Using neural networks such as FinNet and dynamic recurrent neural decoders, the work aims to better extract and translate brain activity into movement while creating low-power hardware capable of supporting long-term practical neuroprosthetic applications.

This research develops photonic integrated circuits that compute using light instead of electrons. By creating integrated all-optical transistors and photonic neural networks, the work advances ultra-fast optical computing systems capable of dramatically outperforming conventional electronic processors in speed, efficiency, and future artificial intelligence applications.

This research explores how artificial intelligence systems can continue learning without forgetting previously acquired knowledge. Instead of erasing old information, the proposed method compresses knowledge into more efficient representations, allowing AI systems such as self-driving cars to adapt safely to new environments while avoiding dangerous performance failures during learning.

This research develops reliable AI-powered drone systems to support New Zealand’s Predator Free 2050 initiative. By improving neural network calibration, uncertainty estimation, and robustness in challenging real-world conditions, the project aims to accurately detect invasive predators and better protect endangered native bird species.

This thesis introduces Armando, a low-cost soft robotic gripper with proprioceptive sensing using a single flexible capacitive sensor and neural-network decoding. Achieving 99% accuracy, Armando enables precise finger-position estimation for applications in prosthetics, assistive care, and disaster response, advancing accessible tactile robotics inspired by human touch.