Training deep neural networks with low precision input data: a hurricane prediction case study
Visualitza/Obre
10.1007/978-3-030-02465-9_40
Inclou dades d'ús des de 2022
Cita com:
hdl:2117/132833
Tipus de documentText en actes de congrés
Data publicació2018
EditorSpringer
Condicions d'accésAccés obert
Tots els drets reservats. Aquesta obra està protegida pels drets de propietat intel·lectual i
industrial corresponents. Sense perjudici de les exempcions legals existents, queda prohibida la seva
reproducció, distribució, comunicació pública o transformació sense l'autorització del titular dels drets
Abstract
Training deep neural networks requires huge amounts of data. The next generation of intelligent systems will generate and utilise massive amounts of data which will be transferred along machine learning workflows. We study the effect of reducing the precision of this data at early stages of the workflow (i.e. input) on both prediction accuracy and learning behaviour of deep neural networks. We show that high precision data can be transformed to low precision before feeding it to a neural network model with insignificant depreciation in accuracy. As such, a high precision representation of input data is not entirely necessary for some applications. The findings of this study pave way for the application of deep learning in areas where acquiring high precision data is difficult due to both memory and computational power constraints. We further use a hurricane prediction case study where we predict the monthly number of hurricanes on the Atlantic Ocean using deep neural networks. We train a deep neural network model that predicts the number of hurricanes, first, by using high precision input data and then by using low precision data. This leads to only a drop in prediction accuracy of less than 2%.
CitacióKahira, A.; Bautista-Gómez, L.; Badia, R.M. Training deep neural networks with low precision input data: a hurricane prediction case study. A: International Conference on High Performance Computing. "High Performance Computing: ISC High Performance 2018 International Workshops: Frankfurt/Main, Germany, June 28, 2018: revised selected papers". Berlín: Springer, 2019, p. 562-569.
ISBN978-3-030-02465-9
Versió de l'editorhttps://link.springer.com/chapter/10.1007/978-3-030-02465-9_40
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
Training+Deep+Neural+Networks.pdf | 271,2Kb | Visualitza/Obre |