Abstract
This concerns the estimation of physical parameters characterizing the ocean bottom from parallel time series representing (A) the instantaneous height of the water column above a section of bottom and (B) the vertical displacement of the bottom section from its long term average. Time series A, representing wind-generated waves, is modeled by a sinusoid with phase jitter. In the absence of both seismic background noise and any nonlinear behavior in the ocean bottom, time series B could be modeled by coupling the bottom through a spring and dashpot to a mass proportional to A. We created two- and three-layer adaptive networks in which series A and B (with lag) were inputs. Training consisted in subtracting the network output from the current value of series B and feeding back these errors in accordance with the appropriate formulas for gradient descent in squared error. The trained nets act as models of the way in which the bottom responds to changes at the surface.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of SPIE - The International Society for Optical Engineering |
| Place of Publication | Bellingham, WA, United States |
| Publisher | Publ by Int Soc for Optical Engineering |
| Pages | 52-63 |
| Number of pages | 12 |
| Volume | 1700 |
| ISBN (Print) | 0819408654 |
| Publication status | Published - 1992 Dec 1 |
| Externally published | Yes |
| Event | Automatic Object Recognition II - Orlando, FL, USA Duration: 1992 Apr 22 → 1992 Apr 24 |
Other
| Other | Automatic Object Recognition II |
|---|---|
| City | Orlando, FL, USA |
| Period | 92/4/22 → 92/4/24 |
Fingerprint
ASJC Scopus subject areas
- Electrical and Electronic Engineering
- Condensed Matter Physics
Cite this
Neural network for ocean bottom parameter estimation. / Baran, Robert H.; Ko, Hanseok.
Proceedings of SPIE - The International Society for Optical Engineering. Vol. 1700 Bellingham, WA, United States : Publ by Int Soc for Optical Engineering, 1992. p. 52-63.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Neural network for ocean bottom parameter estimation
AU - Baran, Robert H.
AU - Ko, Hanseok
PY - 1992/12/1
Y1 - 1992/12/1
N2 - This concerns the estimation of physical parameters characterizing the ocean bottom from parallel time series representing (A) the instantaneous height of the water column above a section of bottom and (B) the vertical displacement of the bottom section from its long term average. Time series A, representing wind-generated waves, is modeled by a sinusoid with phase jitter. In the absence of both seismic background noise and any nonlinear behavior in the ocean bottom, time series B could be modeled by coupling the bottom through a spring and dashpot to a mass proportional to A. We created two- and three-layer adaptive networks in which series A and B (with lag) were inputs. Training consisted in subtracting the network output from the current value of series B and feeding back these errors in accordance with the appropriate formulas for gradient descent in squared error. The trained nets act as models of the way in which the bottom responds to changes at the surface.
AB - This concerns the estimation of physical parameters characterizing the ocean bottom from parallel time series representing (A) the instantaneous height of the water column above a section of bottom and (B) the vertical displacement of the bottom section from its long term average. Time series A, representing wind-generated waves, is modeled by a sinusoid with phase jitter. In the absence of both seismic background noise and any nonlinear behavior in the ocean bottom, time series B could be modeled by coupling the bottom through a spring and dashpot to a mass proportional to A. We created two- and three-layer adaptive networks in which series A and B (with lag) were inputs. Training consisted in subtracting the network output from the current value of series B and feeding back these errors in accordance with the appropriate formulas for gradient descent in squared error. The trained nets act as models of the way in which the bottom responds to changes at the surface.
UR - http://www.scopus.com/inward/record.url?scp=0027000517&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0027000517&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:0027000517
SN - 0819408654
VL - 1700
SP - 52
EP - 63
BT - Proceedings of SPIE - The International Society for Optical Engineering
PB - Publ by Int Soc for Optical Engineering
CY - Bellingham, WA, United States
ER -