Deep echo state network (deepesn): A brief survey

C Gallicchio, A Micheli - arxiv preprint arxiv:1712.04323, 2017‏ - arxiv.org
The study of deep recurrent neural networks (RNNs) and, in particular, of deep Reservoir
Computing (RC) is gaining an increasing research attention in the neural networks …

Deep randomized neural networks

C Gallicchio, S Scardapane - Recent Trends in Learning From Data …, 2020‏ - Springer
Abstract Randomized Neural Networks explore the behavior of neural systems where the
majority of connections are fixed, either in a stochastic or a deterministic fashion. Typical …

Minimum complexity echo state network

A Rodan, P Tino - IEEE transactions on neural networks, 2010‏ - ieeexplore.ieee.org
Reservoir computing (RC) refers to a new class of state-space models with a fixed state
transition structure (the reservoir) and an adaptable readout form the state space. The …

Echo state property of deep reservoir computing networks

C Gallicchio, A Micheli - Cognitive Computation, 2017‏ - Springer
In the last years, the Reservoir Computing (RC) framework has emerged as a state of-the-art
approach for efficient learning in temporal domains. Recently, within the RC context, deep …

An experimental characterization of reservoir computing in ambient assisted living applications

D Bacciu, P Barsocchi, S Chessa, C Gallicchio… - Neural Computing and …, 2014‏ - Springer
In this paper, we present an introduction and critical experimental evaluation of a reservoir
computing (RC) approach for ambient assisted living (AAL) applications. Such an empirical …

Sparse random neural networks for online anomaly detection on sensor nodes

S Leroux, P Simoens - Future Generation Computer Systems, 2023‏ - Elsevier
Whether it is used for predictive maintenance, intrusion detection or surveillance, on-device
anomaly detection is a very valuable functionality in sensor and Internet-of-things (IoT) …

Markovian architectural bias of recurrent neural networks

P Tino, M Cernansky… - IEEE Transactions on …, 2004‏ - ieeexplore.ieee.org
In this paper, we elaborate upon the claim that clustering in the recurrent layer of recurrent
neural networks (RNNs) reflects meaningful information processing states even prior to …

Blind construction of optimal nonlinear recursive predictors for discrete sequences

C Shalizi, KL Klinkner - arxiv preprint arxiv:1408.2025, 2014‏ - arxiv.org
We present a new method for nonlinear prediction of discrete random sequences under
minimal structural assumptions. We give a mathematical construction for optimal predictors …

Simple deterministically constructed cycle reservoirs with regular jumps

A Rodan, P Tiňo - Neural computation, 2012‏ - ieeexplore.ieee.org
A new class of state-space models, reservoir models, with a fixed state transition structure
(the “reservoir”) and an adaptable readout from the state space, has recently emerged as a …

Financial volatility trading using recurrent neural networks

P Tino, C Schittenkopf, G Dorffner - IEEE transactions on …, 2001‏ - ieeexplore.ieee.org
We simulate daily trading of straddles on financial indexes. The straddles are traded based
on predictions of daily volatility differences in the indexes. The main predictive models …