Newest papers

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

Erik Stolt, Sanja Karilanova, Ayça Özçelikkale · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28495 · cited by 0 works (OpenAlex) · open-access PDF

Indonesian

Deep State-Space Competed Models (Deep SSMs) telah menunjukkan kinerja dan manfaat komputasi yang menjanjikan dalam memproses data-seri waktu dengan ketergantungan waktu yang kompleks. Jaringan saraf spasial (SNNs) yang menggambarkan kelas SSM yang terinspirasi secara biologis, di mana blok komputasi berkomunikasi melalui spikes, peristiwa-peristiwa single-bit yang terpisah daripada fungsi aktivasi berkelanjutan. Tugas yang sangat penting dalam pemrosesan waktu-seri yang kompleks adalah memprediksi antara, yaitu memprediksi nilai-nilai masa depan dari urutan yang diusulkan dari pengamatan masa lalu saja. Namun, bagaimana untuk melakukan prediksi dengan SNNs adalah pertanyaan terbuka, di mana sifat autoregresif standar dari pemrosesan data dengan SNNs memerlukan nilai-nilai yang tidak tersedia selama fase prediksi.

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 the standard autoregressive nature of the data processing with SNNs requires values that are not available during the forecasting phase. In this article, we address this challenge. We explore two closed-loop forecasting strategies, in which the network's own generated values are fed back into the network as if they were observed past values: (i) model-level and (ii) layer-level closed-loop forecasting. We evaluate these approaches on the ETT-small datasets, a standard benchmark for time-series forecasting, under both spike-based and continuous activation functions. We compare the proposed closed-loop approaches against state-of-the-art methods such as SpaceTime, as well as the zero-masking baseline in S4. Both of the proposed approaches perform comparably to or better than zero-masking with S4, and in most cases match SpaceTime. These findings highlight the trade-off between continuous and low-bit quantized activations, and demonstrate that the proposed Deep SSM architectures provide a competitive framework for forecasting.

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

Topics: Computer science, Benchmark (surveying), Spiking neural network, Artificial intelligence, Artificial neural network, Deep learning

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