Newest papers

Model- and Layer-Level Closed-Loop Forecasting with SSM-Based Spiking Neural Networks

Erik Stolt, Sanja Karilanova, Ayca Ozcelikkale · 2026 · arXiv

DOI: 10.48550/arXiv.2610.28495 · open-access PDF

Spanish

Los modelos Deep State-Space (Deep SSMs) han demostrado un rendimiento prometedor y beneficios computacionales en el procesamiento de datos de series temporales con dependencias temporales complejas. Las redes neuronales de punta (SNNs) constituyen una clase biológicamente inspirada de SSMs profundos, donde los bloques computacionales comunican a través de picos, eventos discretos de bits únicos en lugar de funciones de activación continua. Una tarea particularmente importante en el procesamiento de series temporales es la predicción, es decir, la predicción de los valores futuros de una secuencia a partir de observaciones pasadas solas.

Machine translation (Meta M2M100); the English original follows.

Abstract

Deep State-Space Models (Deep SSMs) have shown promising performance and computational benefits in processing of time-series data with complex temporal dependencies. Spiking neural networks (SNNs) constitute a biologically inspired class of deep SSMs, where computing blocks communicate through spikes, discrete single-bit events rather than continuous activation functions. A particularly important task in time-series processing is forecasting, i.e. predicting future values of a sequence from past observations alone. However, how to best perform forecasting with SNNs is an open question, where t

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange