arXiv:2510.20997v1 Announce Type: new 
Abstract: We present a general framework for training spiking neural networks (SNNs) to perform binary classification on multivariate time series, with a focus on step-wise prediction and high precision at low false alarm rates. The approach uses the Evolutionary Optimization of Neuromorphic Systems (EONS) algorithm to evolve sparse, stateful SNNs by jointly optimizing their architectures and parameters. Inputs are encoded into spike trains, and predictions are made by thresholding a single output neuron's spike counts. We also incorporate simple voting ensemble methods to improve performance and robustness.
  To evaluate the framework, we apply it with application-specific optimizations to the task of detecting low signal-to-noise ratio radioactive sources in gamma-ray spectral data. The resulting SNNs, with as few as 49 neurons and 66 synapses, achieve a 51.8% true positive rate (TPR) at a false alarm rate of 1/hr, outperforming PCA (42.7%) and deep learning (49.8%) baselines. A three-model any-vote ensemble increases TPR to 67.1% at the same false alarm rate. Hardware deployment on the microCaspian neuromorphic platform demonstrates 2mW power consumption and 20.2ms inference latency.
  We also demonstrate generalizability by applying the same framework, without domain-specific modification, to seizure detection in EEG recordings. An ensemble achieves 95% TPR with a 16% false positive rate, comparable to recent deep learning approaches with significant reduction in parameter count.

تم تقديم إطار عمل جديد لتدريب الشبكات العصبية النابضة (SNN) لتصنيف النتائج الثنائية بشكل فعال في بيانات السلاسل الزمنية متعددة المتغيرات. يركز هذا النهج المبتكر على التنبؤ خطوة بخطوة ويهدف إلى تحقيق دقة عالية مع تقليل الإنذارات الكاذبة. من خلال استخدام خوارزمية تحسين تطورية للأنظمة العصبية (EONS)، يقوم الإطار بتطوير SNNs نادرة وحالة، مع تحسين كل من هيكلها ومعلماتها. هذه الخطوة مهمة لأنها تعزز قدرات SNNs في التطبيقات الزمنية الحقيقية، مما يجعلها أكثر موثوقية في عمليات اتخاذ القرار الحرجة.

Se ha introducido un nuevo marco para entrenar redes neuronales de picos (SNN) para clasificar eficazmente resultados binarios en datos de series temporales multivariadas. Este enfoque innovador enfatiza la predicción paso a paso y busca alta precisión mientras minimiza las falsas alarmas. Al utilizar el algoritmo de Optimización Evolutiva de Sistemas Neuromórficos (EONS), el marco evoluciona SNN escasos y con estado, optimizando tanto su arquitectura como sus parámetros. Este avance es significativo ya que mejora las capacidades de los SNN en aplicaciones en tiempo real, haciéndolos más confiables para procesos críticos de toma de decisiones.

Un nouveau cadre a été introduit pour former des réseaux de neurones à impulsions (SNN) afin de classer efficacement des résultats binaires dans des données de séries temporelles multivariées. Cette approche innovante met l'accent sur la prédiction étape par étape et vise une haute précision tout en minimisant les fausses alertes. En utilisant l'algorithme d'optimisation évolutive des systèmes neuromorphiques (EONS), le cadre fait évoluer des SNN rares et à état, optimisant à la fois leur architecture et leurs paramètres. Cette avancée est significative car elle améliore les capacités des SNN dans des applications en temps réel, les rendant plus fiables pour des processus de prise de décision critiques.

A new framework has been introduced for training spiking neural networks (SNNs) to effectively classify binary outcomes in multivariate time series data. This innovative approach emphasizes step-wise prediction and aims for high precision while minimizing false alarms. By utilizing the Evolutionary Optimization of Neuromorphic Systems (EONS) algorithm, the framework evolves sparse and stateful SNNs, optimizing both their architecture and parameters. This advancement is significant as it enhances the capabilities of SNNs in real-time applications, making them more reliable for critical decision-making processes.

Exploring Spiking Neural Networks for Binary Classification in Multivariate Time Series at the Edge

arXiv:2601.08447v1 Announce Type: cross 
Abstract: Spike-timing-dependent plasticity (STDP) provides a biologically-plausible learning mechanism for spiking neural networks (SNNs); however, Hebbian weight updates in architectures with recurrent connections suffer from pathological weight dynamics: unbounded growth, catastrophic forgetting, and loss of representational diversity. We propose a neuromorphic regularization scheme inspired by the synaptic homeostasis hypothesis: periodic offline phases during which external inputs are suppressed, synaptic weights undergo stochastic decay toward a homeostatic baseline, and spontaneous activity enables memory consolidation. We demonstrate that this sleep-wake cycle prevents weight saturation while preserving learned structure. Empirically, we find that low to intermediate sleep durations (10-20\% of training) improve stability on MNIST-like benchmarks in our STDP-SNN model, without any data-specific hyperparameter tuning. In contrast, the same sleep intervention yields no measurable benefit for the surrogate-gradient spiking neural network (SG-SNN). Taken together, these results suggest that periodic, sleep-based renormalization may represent a fundamental mechanism for stabilizing local Hebbian learning in neuromorphic systems, while also indicating that special care is required when integrating such protocols with existing gradient-based optimization methods.

تشير دراسة جديدة إلى اقتراح نظام تنظيم منزلي قائم على النوم لاستقرار البلاستيك المعتمد على توقيت النبضات (STDP) في الشبكات العصبية النابضة المتكررة (SNNs). تهدف هذه الطريقة إلى التخفيف من مشكلات مثل النمو غير المحدود للأوزان والنسيان الكارثي من خلال إدخال مراحل غير نشطة حيث تتراجع الأوزان المشبكية نحو خط الأساس المنزلي، مما يعزز من دمج الذاكرة.

Un nuevo estudio propone un esquema de regularización homeostática basado en el sueño para estabilizar la plasticidad dependiente del tiempo de picos (STDP) en redes neuronales recurrentes de picos (SNNs). Este enfoque busca mitigar problemas como el crecimiento ilimitado de pesos y el olvido catastrófico al introducir fases fuera de línea donde los pesos sinápticos decaen hacia una línea base homeostática, mejorando así la consolidación de la memoria.

Une nouvelle étude propose un schéma de régularisation homéostatique basé sur le sommeil pour stabiliser la plasticité dépendante du timing des pics (STDP) dans les réseaux neuronaux à pics récurrents (SNNs). Cette approche vise à atténuer des problèmes tels que la croissance illimitée des poids et l'oubli catastrophique en introduisant des phases hors ligne où les poids synaptiques décroissent vers une ligne de base homéostatique, améliorant ainsi la consolidation de la mémoire.

A new study proposes a sleep-based homeostatic regularization scheme to stabilize spike-timing-dependent plasticity (STDP) in recurrent spiking neural networks (SNNs). This approach aims to mitigate issues such as unbounded weight growth and catastrophic forgetting by introducing offline phases where synaptic weights decay towards a homeostatic baseline, enhancing memory consolidation.

Sleep-Based Homeostatic Regularization for Stabilizing Spike-Timing-Dependent Plasticity in Recurrent Spiking Neural Networks

One More Thing in AI – Your Shortcut to AI Mastery

Exploring Spiking Neural Networks for Binary Classification in Multivariate Time Series at the Edge

Was this article worth reading? Share it

One More Thing in AI

LucidQuery AI

Graphite Note

Hypertune

Solvice

MyCVBot

Ready to build your own newsroom?