Saved in:
Bibliographic Details
Main Authors: Chakraborty, Biswadeep, Mukhopadhyay, Saibal
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.01257
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913771906138112
author Chakraborty, Biswadeep
Mukhopadhyay, Saibal
author_facet Chakraborty, Biswadeep
Mukhopadhyay, Saibal
contents We propose \textbf{FLAMES (Fast Long-range Adaptive Memory for Event-based Systems)}, a novel hybrid framework integrating structured state-space dynamics with event-driven computation. At its core, the \textit{Spike-Aware HiPPO (SA-HiPPO) mechanism} dynamically adjusts memory retention based on inter-spike intervals, preserving both short- and long-range dependencies. To maintain computational efficiency, we introduce a normal-plus-low-rank (NPLR) decomposition, reducing complexity from $\mathcal{O}(N^2)$ to $\mathcal{O}(Nr)$. FLAMES achieves state-of-the-art results on the Long Range Arena benchmark and event datasets like HAR-DVS and Celex-HAR. By bridging neuromorphic computing and structured sequence modeling, FLAMES enables scalable long-range reasoning in event-driven systems.
format Preprint
id arxiv_https___arxiv_org_abs_2504_01257
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FLAMES: A Hybrid Spiking-State Space Model for Adaptive Memory Retention in Event-Based Learning
Chakraborty, Biswadeep
Mukhopadhyay, Saibal
Machine Learning
We propose \textbf{FLAMES (Fast Long-range Adaptive Memory for Event-based Systems)}, a novel hybrid framework integrating structured state-space dynamics with event-driven computation. At its core, the \textit{Spike-Aware HiPPO (SA-HiPPO) mechanism} dynamically adjusts memory retention based on inter-spike intervals, preserving both short- and long-range dependencies. To maintain computational efficiency, we introduce a normal-plus-low-rank (NPLR) decomposition, reducing complexity from $\mathcal{O}(N^2)$ to $\mathcal{O}(Nr)$. FLAMES achieves state-of-the-art results on the Long Range Arena benchmark and event datasets like HAR-DVS and Celex-HAR. By bridging neuromorphic computing and structured sequence modeling, FLAMES enables scalable long-range reasoning in event-driven systems.
title FLAMES: A Hybrid Spiking-State Space Model for Adaptive Memory Retention in Event-Based Learning
topic Machine Learning
url https://arxiv.org/abs/2504.01257