# Enhancing Time-Series Anomaly Detection by Integrating Spectral-Residual Bottom-Up Attention with Reservoir Computing

arXiv: https://arxiv.org/abs/2510.14287 · HTML: https://mlsanity.com/paper/2510.14287/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 105 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Builds on (most cited first, 24 of 24)

- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Deep Learning in Neural Networks: An Overview](https://mlsanity.com/paper/1404.7828/) (2014)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019](https://mlsanity.com/paper/1911.13288/) (2019)
- [Deep Learning for Time Series Anomaly Detection: A Survey](https://mlsanity.com/paper/2211.05244/) (2022)
- [Explainable Deep One-Class Classification](https://mlsanity.com/paper/2007.01760/) (2020)
- [Deep Learning for Medical Anomaly Detection -- A Survey](https://mlsanity.com/paper/2012.02364/) (2020)
- [Salient Object Detection: A Survey](https://mlsanity.com/paper/1411.5878/) (2014)
- [Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence](https://mlsanity.com/paper/1909.00560/) (2019)
- [Toward Supervised Anomaly Detection](https://mlsanity.com/paper/1401.6424/) (2014)
- [A General Survey on Attention Mechanisms in Deep Learning](https://mlsanity.com/paper/2203.14263/) (2022)
- [Physical reservoir computing -- An introductory perspective](https://mlsanity.com/paper/2005.00992/) (2020)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [Rethinking Assumptions in Deep Anomaly Detection](https://mlsanity.com/paper/2006.00339/) (2020)
- [A Survey on Efficient Training of Transformers](https://mlsanity.com/paper/2302.01107/) (2023)
- [Efficient Multi-User Computation Offloading for Mobile-Edge Cloud Computing](https://mlsanity.com/paper/1510.00888/) (2015)
- [A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning](https://mlsanity.com/paper/2307.15092/) (2023)
- [Edge AI: A Taxonomy, Systematic Review and Future Directions](https://mlsanity.com/paper/2407.04053/) (2024)
- [Analog In-Memory Computing Attention Mechanism for Fast and Energy-Efficient Large Language Models](https://mlsanity.com/paper/2409.19315/) (2024)
- [Series Saliency: Temporal Interpretation for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2012.09324/) (2020)
- [Learning Reservoir Dynamics with Temporal Self-Modulation](https://mlsanity.com/paper/2301.09235/) (2023)
- [Attention-Enhanced Reservoir Computing](https://mlsanity.com/paper/2312.16503/) (2023)
- [Research and application of Transformer based anomaly detection model: A literature review](https://mlsanity.com/paper/2402.08975/) (2024)

## Abstract (arXiv)

Reservoir computing (RC) establishes the basis for the processing of time-series data by exploiting the high-dimensional spatiotemporal response of a recurrent neural network to an input signal. In particular, RC trains only the output layer weights. This simplicity has drawn attention especially in Edge Artificial Intelligence (AI) applications. Edge AI enables time-series anomaly detection in real time, which is important because detection delays can lead to serious incidents. However, achieving adequate anomaly-detection performance with RC alone may require an unacceptably large reservoir on resource-constrained edge devices. Without enlarging the reservoir, attention mechanisms can improve accuracy, although they may require substantial computation and undermine the learning efficiency of RC. In this study, to improve the anomaly detection performance of RC without sacrificing learning efficiency, we propose a spectral residual RC (SR-RC) that integrates the spectral residual (SR) method - a learning-free, bottom-up attention mechanism - with RC. We demonstrated that SR-RC outperformed conventional RC and logistic-regression models based on values extracted by the SR method across benchmark tasks and real-world time-series datasets. Moreover, because the SR method, similarly to RC, is well suited for hardware implementation, SR-RC suggests a practical direction for deploying RC as Edge AI for time-series anomaly detection.