.png){kind=icon}
返回
Efficient Implementations of Echo State Network Cross-Validation
.png){kind=icon}
PRE
AI
DOI：10.1007/s12559-021-09849-2.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Cross-Validation (CV) is still uncommon in time series modeling. Echo State Networks (ESNs), as a prime example of Reservoir Computing (RC) models, are known for their fast and precise one-shot learning, that often benefit from good hyper-parameter tuning. This makes them ideal to change the status quo. We discuss CV of time series for predicting a concrete time interval of interest, suggest several schemes for cross-validating ESNs and introduce an efficient algorithm for implementing them. This algorithm is presented as two levels of optimizations of doing k-fold CV. Training an RC model typically consists of two stages: (i) running the reservoir with the data and (ii) computing the optimal readouts. The first level of our optimization addresses the most computationally expensive part (i) and makes it remain constant irrespective of k. It dramatically reduces reservoir computations in any type of RC system and is enough if k is small. The second level of optimization also makes the (ii) part remain constant irrespective of large k, as long as the dimension of the output is low. We discuss when the proposed validation schemes for ESNs could be beneficial, three options for producing the final model and empirically investigate them on six different real-world datasets, as well as do empirical computation time experiments. We provide the code in an online repository. Proposed CV schemes give better and more stable test performance in all the six different real-world datasets, three task types. Empirical run times confirm our complexity analysis. In most situations, k-fold CV of ESNs and many other RC models can be done for virtually the same time and space complexity as a simple single-split validation. This enables CV to become a standard practice in RC.
Keyword:
Echo state networks
Reservoir computing
Recurrent neural networks
Cross-validation
Time complexity
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
4.3
论文数:
1.6K
被引数:
3.6K
机构
引用论文
分享收藏<title>Integrated optical Butler matrix for beam forming in phased-array antennas</title>集成光学巴特勒矩阵在相控阵天线中的波束形成
PREAI
分享收藏
Effects of Elevated CO2 on a Natural Diatom Community in the Subtropical NE AtlanticCO2升高对亚热带东北大西洋天然硅藻群落的影响
OAAI
OAAI分享收藏Optimization and applications of echo state networks with leaky-integrator neurons具有漏积分神经元的回声状态网络的优化及应用.png)
NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏
查看更多内容