Abstract | ||
---|---|---|
We create an artificial neural network which is a version of echo state machines, ESNs. ESNs are recurrent neural networks but unlike most recurrent networks, they come with an efficient training method. We have previously [17] adapted this method using ideas from neuroscale [15] so that the network is optimal for projecting multivariate time series data onto a low dimensional manifold so that the structure in the time series can be identified by eye. In this paper, we investigate a minimal architecture echo state machine in the context of visualisation and show that it does not perform as well as the original. Using a financial time series, we investigate 3 methods for regaining the power of the standard echo state machine. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/CIS.2011.91 | CIS |
Keywords | Field | DocType |
finite state machines,echo state machine,standard echo state machine,learning (artificial intelligence),efficient training method,financial data processing,recurrent neural networks,minimal architecture echo state machine,financial time series,data visualisation,multivariate time series data,minimal echo state networks,artificial neural network,recurrent network,recurrent neural nets,recurrent neural network,minimal architecture echo state,time series,neuroscale,training method,esn,data visualization,echo state network,reservoirs,state machine,euclidean distance,learning artificial intelligence,training data | Time series,Data visualization,Visualization,Computer science,Euclidean distance,Recurrent neural network,Finite-state machine,Artificial intelligence,Artificial neural network,Machine learning,Manifold | Conference |
ISBN | Citations | PageRank |
978-1-4577-2008-6 | 1 | 0.40 |
References | Authors | |
3 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tzai-der Wang | 1 | 119 | 15.65 |
Xiaochuan Wu | 2 | 2 | 1.11 |
Colin Fyfe | 3 | 324 | 35.74 |