A Prediction Method Based on Improved Echo State Network for COVID-19 Nonlinear Time Series

Liu, Banteng; Chen, Wei; Chen, Yourong; Ping, Sun; Jin, Heli; Chen, Hao

doi:10.4236/jcc.2020.812011

Cited by 1 publication

(1 citation statement)

References 7 publications

(5 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the firing rates of MSTd neurons encoding the relative importance of the core features to the current visual input are transferred to the readout decision model. In this paper, an echo state network (ESN) proposed by Jaeger [30][31][32] is utilized as the decision model. It consists of a random sparse network (reservoir) and one readout layer.…”

Section: Decision Model Of Echo State Networkmentioning

confidence: 99%

A Visually Inspired Computational Model for Recognition of Optic Flow

Li,

Lin,

et al. 2023

Mathematics

View full text Add to dashboard Cite

Foundation models trained on vast quantities of data have demonstrated impressive performance in capturing complex nonlinear relationships and accurately predicting neuronal responses. Due to the fact that deep learning neural networks depend on massive amounts of data samples and high energy consumption, foundation models based on spiking neural networks (SNNs) have the potential to significantly reduce calculation costs by training on neuromorphic hardware. In this paper, a visually inspired computational model composed of an SNN and echo state network (ESN) is proposed for the recognition of optic flow. The visually inspired SNN model serves as a foundation model that is trained using spike-timing-dependent plasticity (STDP) for extracting core features. The ESN model makes readout decisions for recognition tasks using the linear regression method. The results show that STDP can perform similar functions as non-negative matrix decomposition (NMF), i.e., generating sparse and linear superimposed readouts based on basis flow fields. Once the foundation model is fully trained from enough input samples, it can considerably reduce the training samples required for ESN readout learning. Our proposed SNN-based foundation model facilitates efficient and cost-effective task learning and could also be adapted to new stimuli that are not included in the training of the foundation model. Moreover, compared with the NMF algorithm, the foundation model trained using STDP does not need to be retrained during the testing procedure, contributing to a more efficient computational performance.

show abstract

Section: Decision Model Of Echo State Networkmentioning

confidence: 99%