Time-Coded Spiking Fourier Transform in Neuromorphic Hardware

After several decades of continuously optimizing computing systems, the Moore's law is reaching itsend. However, there an increasing demand for fast and efficient processing systems that can handlelarge streams data while decreasing system footprints. Neuromorphic answers thisneed by creating decentralized architectures communicate with binary events over time. Despiteits rapid growth in last few years, novel algorithms are needed leverage potential ofthis emerging paradigm stimulate design advanced neuromorphic chips.In this work, we propose a time-based spiking neural network mathematically equivalent tothe Fourier transform. We implemented chip Loihi conductedexperiments on five different real scenarios automotive frequency modulated continuouswave radar. Experimental results validate algorithm, hope they prompt adhoc chips improve efficiency state-of-the-art digital signal processorsand encourage research processing.