Efficient Neuromorphic Signal Processing with Loihi 2

TL;DR

This paper demonstrates how Loihi 2's programmable spiking neurons enable efficient neuromorphic processing, achieving significant reductions in bandwidth and computational complexity for tasks like Fourier transforms, optical flow, and audio classification.

Contribution

It introduces advanced spiking neuron models on Loihi 2 that enable efficient streaming data processing with novel applications and preliminary training results.

Findings

RF neurons compute STFT with 47x less bandwidth

Optical flow estimation requires 90x fewer operations

Preliminary backpropagation training for audio classification

Abstract

The biologically inspired spiking neurons used in neuromorphic computing are nonlinear filters with dynamic state variables -- very different from the stateless neuron models used in deep learning. The next version of Intel's neuromorphic research processor, Loihi 2, supports a wide range of stateful spiking neuron models with fully programmable dynamics. Here we showcase advanced spiking neuron models that can be used to efficiently process streaming data in simulation experiments on emulated Loihi 2 hardware. In one example, Resonate-and-Fire (RF) neurons are used to compute the Short Time Fourier Transform (STFT) with similar computational complexity but 47x less output bandwidth than the conventional STFT. In another example, we describe an algorithm for optical flow estimation using spatiotemporal RF neurons that requires over 90x fewer operations than a conventional DNN-based solution. We also demonstrate promising preliminary results using backpropagation to train RF neurons for audio classification tasks. Finally, we show that a cascade of Hopf resonators - a variant of the RF neuron - replicates novel properties of the cochlea and motivates an efficient spike-based spectrogram encoder.