Hardware spiking neural network and remote FPGA lab

The automatic design of intelligent systems has been inspired by biology, specifically the operation of the human brain. Researchers hope to exploit and replicate the brain's ability to adapt and self repair in order to develop robust and error tolerant embedded hardware computational devices. Spiking Neural Networks (SNNs) emulate neural behaviour observed in biology. This thesis describes the successful development of a Network-on-Chip based hardware SNN(EMBRACE-FPGA) and the supporting GA-based SNN training and application implementation tools (SNNDevSys). Hardware SNNs can be configured for multiple applications through programming of neuron spike firing threshold potentials, synaptic weights and the hardware SNN interconnection topology. This thesis describes the hardware SNN architecture and prototype and its application to a range of benchmark control and classification problems. This work has contributed to ongoing EMBRACE-FPGA architecture development within the Bio-Inspired and Reconfigurable Computing research group to improve practical hardware SNN scalability. Phase II of this thesis describes the development of the Remote FPGA Laboratory (RFL). In recent years there has been a growing interest in the development of web-based e-learning systems. The RFL is a web-based distance learning application which enables the teaching of digital systems design using real FPGA devices through a standard web browser. The RFL allows users to configure and interact with FPGA devices via the Internet as part of a combined training and evaluation framework. The system has been designed as an interactive learning tool, which aims to increase student interaction and understanding through a learn-by-doing approach. The system enables better understanding of the operation of digital systems through animation of internal signals, real-time timing diagrams and single-stepping of hardware circuits