TY - GEN
T1 - Learning multiscale neural metrics via entropy minimization
AU - Brockmeier, Austin J.
AU - Giraldo, Luis G.Sanchez
AU - Choi, John S.
AU - Francis, Joseph T.
AU - Principe, Jose C.
PY - 2013
Y1 - 2013
N2 - In order to judiciously compare neural responses between repeated trials or stimuli, a well-suited distance metric is necessary. With multi-electrode recordings, a neural response is a spatiotemporal pattern, but not all of the dimensions of space and time should be treated equally. In order to understand which dimensions of the input are more discriminative and to improve the classification performance, we propose a metric-learning approach that can be used across scales. This extends previous work that used a linear projection into lower dimensional space; here, multiscale metrics or kernels are learned as the weighted combinations of different metrics or kernels on each of the neural response's dimensions. Preliminary results are explored on a cortical recording of a rat during a tactile stimulation experiment. Metrics on both local field potential and spiking data are explored. The learned weights reveal important dimensions of the response, and the learned metrics improve nearest-neighbor classification performance.
AB - In order to judiciously compare neural responses between repeated trials or stimuli, a well-suited distance metric is necessary. With multi-electrode recordings, a neural response is a spatiotemporal pattern, but not all of the dimensions of space and time should be treated equally. In order to understand which dimensions of the input are more discriminative and to improve the classification performance, we propose a metric-learning approach that can be used across scales. This extends previous work that used a linear projection into lower dimensional space; here, multiscale metrics or kernels are learned as the weighted combinations of different metrics or kernels on each of the neural response's dimensions. Preliminary results are explored on a cortical recording of a rat during a tactile stimulation experiment. Metrics on both local field potential and spiking data are explored. The learned weights reveal important dimensions of the response, and the learned metrics improve nearest-neighbor classification performance.
UR - http://www.scopus.com/inward/record.url?scp=84897742038&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84897742038&partnerID=8YFLogxK
U2 - 10.1109/NER.2013.6695918
DO - 10.1109/NER.2013.6695918
M3 - Conference contribution
AN - SCOPUS:84897742038
SN - 9781467319690
T3 - International IEEE/EMBS Conference on Neural Engineering, NER
SP - 247
EP - 250
BT - 2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013
T2 - 2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013
Y2 - 6 November 2013 through 8 November 2013
ER -