Hardware-Friendly Delayed-Feedback Reservoir for Multivariate Time-Series Classification

• URL: http://arxiv.org/abs/2504.11981v1
• Date: Wed, 16 Apr 2025 11:22:38 GMT
• Title: Hardware-Friendly Delayed-Feedback Reservoir for Multivariate Time-Series Classification
• Authors: Sosei Ikeda, Hiromitsu Awano, Takashi Sato,
• Abstract summary: Reservoir computing is attracting attention as a machine-learning technique for edge computing.<n>In time-series classification tasks, the number of features obtained using a reservoir depends on the length of the input series.<n>We propose a dot-product-based reservoir representation (DPR) for RC based on the dot product of data features.
• Score: 3.8861692690368823
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reservoir computing (RC) is attracting attention as a machine-learning technique for edge computing. In time-series classification tasks, the number of features obtained using a reservoir depends on the length of the input series. Therefore, the features must be converted to a constant-length intermediate representation (IR), such that they can be processed by an output layer. Existing conversion methods involve computationally expensive matrix inversion that significantly increases the circuit size and requires processing power when implemented in hardware. In this article, we propose a simple but effective IR, namely, dot-product-based reservoir representation (DPRR), for RC based on the dot product of data features. Additionally, we propose a hardware-friendly delayed-feedback reservoir (DFR) consisting of a nonlinear element and delayed feedback loop with DPRR. The proposed DFR successfully classified multivariate time series data that has been considered particularly difficult to implement efficiently in hardware. In contrast to conventional DFR models that require analog circuits, the proposed model can be implemented in a fully digital manner suitable for high-level syntheses. A comparison with existing machine-learning methods via field-programmable gate array implementation using 12 multivariate time-series classification tasks confirmed the superior accuracy and small circuit size of the proposed method.

Related papers

• Techniques for Enhancing Memory Capacity of Reservoir Computing [0.7421845364041001]
  Reservoir Computing (RC) is a bio-inspired machine learning framework.<n>There is a trade-off between memory capacity and nonlinearity in RC.<n>We propose methods to improve the memory capacity of reservoir models.
  arXiv  Detail & Related papers  (2025-02-25T07:38:58Z)
• ADC/DAC-Free Analog Acceleration of Deep Neural Networks with Frequency Transformation [2.7488316163114823]
  This paper proposes a novel approach to an energy-efficient acceleration of frequency-domain neural networks by utilizing analog-domain frequency-based tensor transformations. Our approach achieves more compact cells by eliminating the need for trainable parameters in the transformation matrix. On a 16$times$16 crossbars, for 8-bit input processing, the proposed approach achieves the energy efficiency of 1602 tera operations per second per Watt.
  arXiv  Detail & Related papers  (2023-09-04T19:19:39Z)
• RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration [73.69415797389195]
  We propose an end-to-end transformer network (RegFormer) for large-scale point cloud alignment. Specifically, a projection-aware hierarchical transformer is proposed to capture long-range dependencies and filter outliers. Our transformer has linear complexity, which guarantees high efficiency even for large-scale scenes.
  arXiv  Detail & Related papers  (2023-03-22T08:47:37Z)
• FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification [53.55504611255664]
  FormerTime is a hierarchical representation model for improving the classification capacity for the multivariate time series classification task. It exhibits three aspects of merits: (1) learning hierarchical multi-scale representations from time series data, (2) inheriting the strength of both transformers and convolutional networks, and (3) tacking the efficiency challenges incurred by the self-attention mechanism.
  arXiv  Detail & Related papers  (2023-02-20T07:46:14Z)
• TransCMD: Cross-Modal Decoder Equipped with Transformer for RGB-D Salient Object Detection [86.94578023985677]
  In this work, we rethink this task from the perspective of global information alignment and transformation. Specifically, the proposed method (TransCMD) cascades several cross-modal integration units to construct a top-down transformer-based information propagation path. Experimental results on seven RGB-D SOD benchmark datasets demonstrate that a simple two-stream encoder-decoder framework can surpass the state-of-the-art purely CNN-based methods.
  arXiv  Detail & Related papers  (2021-12-04T15:45:34Z)
• SreaMRAK a Streaming Multi-Resolution Adaptive Kernel Algorithm [60.61943386819384]
  Existing implementations of KRR require that all the data is stored in the main memory. We propose StreaMRAK - a streaming version of KRR. We present a showcase study on two synthetic problems and the prediction of the trajectory of a double pendulum.
  arXiv  Detail & Related papers  (2021-08-23T21:03:09Z)
• Reservoir Based Edge Training on RF Data To Deliver Intelligent and Efficient IoT Spectrum Sensors [0.6451914896767135]
  We propose a processing architecture that supports general machine learning algorithms on compact mobile devices. Deep Delay Loop Reservoir Computing (DLR) delivers reductions in form factor, hardware complexity and latency, compared to the State-of-the-Art (SoA) We present DLR architectures composed of multiple smaller loops whose state vectors are linearly combined to create a lower dimensional input into Ridge regression.
  arXiv  Detail & Related papers  (2021-04-01T20:08:01Z)
• Reservoir-Based Distributed Machine Learning for Edge Operation [0.6451914896767135]
  We introduce a novel design for in-situ training of machine learning algorithms built into smart sensors. We illustrate distributed training scenarios using radio frequency (RF) spectrum sensors.
  arXiv  Detail & Related papers  (2021-04-01T20:06:40Z)
• Random Feature Attention [69.4671822971207]
  We propose RFA, a linear time and space attention that uses random feature methods to approximate the softmax function. RFA can be used as a drop-in replacement for conventional softmax attention and offers a straightforward way of learning with recency bias through an optional gating mechanism. Experiments on language modeling and machine translation demonstrate that RFA achieves similar or better performance compared to strong transformer baselines.
  arXiv  Detail & Related papers  (2021-03-03T02:48:56Z)
• Deep Cellular Recurrent Network for Efficient Analysis of Time-Series Data with Spatial Information [52.635997570873194]
  This work proposes a novel deep cellular recurrent neural network (DCRNN) architecture to process complex multi-dimensional time series data with spatial information. The proposed architecture achieves state-of-the-art performance while utilizing substantially less trainable parameters when compared to comparable methods in the literature.
  arXiv  Detail & Related papers  (2021-01-12T20:08:18Z)
• Model-Size Reduction for Reservoir Computing by Concatenating Internal States Through Time [2.6872737601772956]
  Reservoir computing (RC) is a machine learning algorithm that can learn complex time series from data very rapidly. To implement RC in edge computing, it is highly important to reduce the amount of computational resources that RC requires. We propose methods that reduce the size of the reservoir by inputting the past or drifting states of the reservoir to the output layer at the current time step.
  arXiv  Detail & Related papers  (2020-06-11T06:11:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.