Matches in UGent Biblio for { <https://biblio.ugent.be/publication/1066010#aggregation> ?p ?o. }
Showing items 1 to 32 of
32
with 100 items per page.
- aggregation classification "P1".
- aggregation creator person.
- aggregation creator person.
- aggregation date "2010".
- aggregation format "application/pdf".
- aggregation hasFormat 1066010.bibtex.
- aggregation hasFormat 1066010.csv.
- aggregation hasFormat 1066010.dc.
- aggregation hasFormat 1066010.didl.
- aggregation hasFormat 1066010.doc.
- aggregation hasFormat 1066010.json.
- aggregation hasFormat 1066010.mets.
- aggregation hasFormat 1066010.mods.
- aggregation hasFormat 1066010.rdf.
- aggregation hasFormat 1066010.ris.
- aggregation hasFormat 1066010.txt.
- aggregation hasFormat 1066010.xls.
- aggregation hasFormat 1066010.yaml.
- aggregation isPartOf urn:isbn:9781424469161.
- aggregation isPartOf urn:isbn:9781424469178.
- aggregation isPartOf urn:issn:1098-7576.
- aggregation language "eng".
- aggregation publisher "IEEE".
- aggregation rights "I have transferred the copyright for this publication to the publisher".
- aggregation subject "Mathematics and Statistics".
- aggregation title "Memory in reservoirs for high dimensional input".
- aggregation abstract "Reservoir Computing (RC) is a recently introduced scheme to employ recurrent neural networks while circumventing the difficulties that typically appear when training the recurrent weights. The ‘reservoir’ is a fixed randomly initiated recurrent network which receives input via a random mapping. Only an instantaneous linear mapping from the network to the output is trained which can be done with linear regression. In this paper we study dynamical properties of reservoirs receiving a high number of inputs. More specifically, we investigate how the internal state of the network retains fading memory of its input signal. Memory properties for random recurrent networks have been thoroughly examined in past research, but only for one-dimensional input. Here we take into account statistics which will typically occur in high dimensional signals. We find useful empirical data which expresses how memory in recurrent networks is distributed over the individual principal components of the input.".
- aggregation authorList BK215447.
- aggregation aggregates 1066032.
- aggregation isDescribedBy 1066010.
- aggregation similarTo IJCNN.2010.5596884.
- aggregation similarTo LU-1066010.