Parameter Sharing for Spatio-Temporal Process Models
While probabilistic models such as Markov random fields can be highly beneficial for spatio-temporal data, they often suffer from over- fitting and have limited use in memory-constrained systems. We present a novel method to compress trained models based on temporal parameter sharing, which reduces redundancies in the parameters.
- Published in:
LWDA Lernen. Wissen. Daten. Analysen. (LWDA) - Type:
Inproceedings - Authors:
R. Fischer, N. Piatkowski, K. Morik - Year:
2019
Citation information
R. Fischer, N. Piatkowski, K. Morik: Parameter Sharing for Spatio-Temporal Process Models, Lernen. Wissen. Daten. Analysen. (LWDA), LWDA, 2019, https://ceur-ws.org/Vol-2454/, Fischer.etal.2019,
@Inproceedings{Fischer.etal.2019,
author={R. Fischer, N. Piatkowski, K. Morik},
title={Parameter Sharing for Spatio-Temporal Process Models},
booktitle={Lernen. Wissen. Daten. Analysen. (LWDA)},
journal={LWDA},
url={https://ceur-ws.org/Vol-2454/},
year={2019},
abstract={While probabilistic models such as Markov random fields can be highly beneficial for spatio-temporal data, they often suffer from over- fitting and have limited use in memory-constrained systems. We present a novel method to compress trained models based on temporal parameter sharing, which reduces redundancies in the...}}