Results 81 to 90 of about 3,514 (178)

A hybrid annual runoff prediction model using echo state network and gated recurrent unit based on sand cat swarm optimization with Markov chain error correction method

Journal of Hydroinformatics
This study proposes a hybrid model based on the combination of Sand Cat Swarm Optimization (SCSO), Echo State Network (ESN), Gated Recurrent Unit (GRU), Least Squares Method (LSM), and Markov Chain (MC) to improve the accuracy of annual runoff prediction.
Jun Wang, Wenchuan Wang, Xiao-xue Hu, Miao Gu, Yang-hao Hong, Hong-fei Zang   +5 more
doaj   +1 more source

A hierarchy of recurrent networks for speech recognition [PDF]

, 2009
Generative models for sequential data based on directed graphs of Restricted Boltzmann Machines (RBMs) are able to accurately model high dimensional sequences as recently shown. In these models, temporal dependencies in the input are discovered by either
Buesing, Lars, Schrauwen, Benjamin
core   +1 more source

Efficient Optimization of Echo State Networks for Time Series Datasets

, 2019
Echo State Networks (ESNs) are recurrent neural networks that only train their output layer, thereby precluding the need to backpropagate gradients through time, which leads to significant computational gains.
Gianniotis, Nikos, Maat, Jacob Reinier, Protopapas, Pavlos   +2 more
core   +1 more source

Molecular mechanisms of plant NLR activation and signalling

The Plant Journal, Volume 125, Issue 3, February 2026.
SUMMARY Plants rely on NLRs (nucleotide‐binding leucine‐rich repeat receptors) to recognise effector proteins secreted by pathogens into plant cells and to deliver disease resistance. Plant NLRs are broadly characterised by their N‐terminal domains, which include the TIR (Toll/interleukin‐1 receptor) and the CC (coiled‐coil) domains.
Natsumi Maruta, Mitchell Sorbello, Laura Garzon‐Flores, Bostjan Kobe   +3 more
wiley   +1 more source

Spatiotemporal Reservoir Computing with a Reconfigurable Multifunctional Memristor Array

Advanced Materials, Volume 38, Issue 3, 13 January 2026.
This study presents a hardware physical reservoir computing system using a tri‐modal memristive crossbar array. Stochastic masking, bistable nonlinear activation, and analog readout enable fully in‐memory spatiotemporal processing. Demonstrations on cellular automata, Lorenz prediction, ADHD EEG classification, and chaotic KS modeling highlight its ...
Sungho Kim, Dong Hoon Shin, Wonho Choi, Sunwoo Cheong, Sung Keun Shim, Soo Hyung Lee, Janguk Han, Yoon Ho Jang, Kunhee Son, Néstor Ghenzi, Cheol Seong Hwang   +10 more
wiley   +1 more source

Short-term prediction of geomagnetic secular variation with an echo state network

Earth, Planets and Space
A technique for predicting the secular variation (SV) of the geomagnetic field based on the echo state network (ESN) model is proposed. SV is controlled by the geodynamo process in the Earth’s outer core, and modeling its nonlinear behaviors can be ...
Shin’ya Nakano, Sho Sato, Hiroaki Toh
doaj   +1 more source

Convolutional Drift Networks for Video Classification

, 2017
Analyzing spatio-temporal data like video is a challenging task that requires processing visual and temporal information effectively. Convolutional Neural Networks have shown promise as baseline fixed feature extractors through transfer learning, a ...
Graham, Dillon, Kanan, Christopher, Kudithipudi, Dhireesha, Langroudi, Seyed Hamed Fatemi   +3 more
core   +1 more source

Comparison of echo state network output layer classification methods on noisy data

, 2017
Echo state networks are a recently developed type of recurrent neural network where the internal layer is fixed with random weights, and only the output layer is trained on specific data.
Prater, Ashley
core   +1 more source

An algorithm for two-dimensional pattern detection by combining Echo State Network-based weak classifiers

Machine Learning with Applications
Pattern detection is one of the essential technologies in computer vision. To solve pattern detection problems, the system needs a vast amount of computational resources.
Hiroshi Kage
doaj   +1 more source

Network Traffic Prediction Using Variational Mode Decomposition and Multi- Reservoirs Echo State Network

IEEE Access, 2019
The network traffic prediction is significant for the network load pre-warning and network congestion control. But the nonlinearity and nonstationarity of the actual network traffic data would reduce the prediction accuracy.
Ying Han, Yuanwei Jing, Kun Li, Georgi Marko Dimirovski   +3 more
doaj   +1 more source