PLEIADES: Building Temporal Kernels with Orthogonal Polynomials

TL;DR

PLEIADES introduces neural networks with orthogonal polynomial-based temporal kernels for efficient, low-latency event-based data classification, achieving state-of-the-art results with reduced computational resources.

Contribution

The paper presents a novel neural network architecture using structured temporal kernels from orthogonal polynomials, enabling flexible data sampling and superior performance on event-based benchmarks.

Findings

Achieved 99.59% accuracy on DVS128 gesture dataset

Attained 99.58% accuracy on AIS eye tracking challenge

Reached 0.556 mAP on PROPHESEE automotive dataset

Abstract

We introduce a class of neural networks named PLEIADES (PoLynomial Expansion In Adaptive Distributed Event-based Systems), which contains temporal convolution kernels generated from orthogonal polynomial basis functions. We focus on interfacing these networks with event-based data to perform online spatiotemporal classification and detection with low latency. By virtue of using structured temporal kernels and event-based data, we have the freedom to vary the sample rate of the data along with the discretization step-size of the network without additional finetuning. We experimented with three event-based benchmarks and obtained state-of-the-art results on all three by large margins with significantly smaller memory and compute costs. We achieved: 1) 99.59% accuracy with 192K parameters on the DVS128 hand gesture recognition dataset and 100% with a small additional output filter; 2) 99.58% test accuracy with 277K parameters on the AIS 2024 eye tracking challenge; and 3) 0.556 mAP with 576k parameters on the PROPHESEE 1 Megapixel Automotive Detection Dataset.