Notes on the Behavior of MC Dropout

Francesco Verdoja; Ville Kyrki

Notes on the Behavior of MC Dropout

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Konferenssiesitys › Scientific › vertaisarvioitu

Abstrakti

Among the various options to estimate uncertainty in deep neural networks, Monte-Carlo dropout is widely popular for its simplicity and effectiveness. However the quality of the uncertainty estimated through this method varies and choices in architecture design and in training procedures have to be carefully considered and tested to obtain satisfactory results. In this paper we present a study offering a different point of view on the behavior of Monte-Carlo dropout, which enables us to observe a few interesting properties of the technique to keep in mind when considering its use for uncertainty estimation.

Alkuperäiskieli	Englanti
Sivumäärä	6
Tila	Julkaistu - 23 heinäk. 2021
OKM-julkaisutyyppi	Ei sovellu
Tapahtuma	ICML Workshop on Uncertainty & Robustness in Deep Learning - Virtual, Online Kesto: 23 heinäk. 2021 → 23 heinäk. 2021 Konferenssinumero: 2021 https://sites.google.com/view/udlworkshop2021

Workshop

Workshop	ICML Workshop on Uncertainty & Robustness in Deep Learning
Lyhennettä	ICML UDL
Kaupunki	Virtual, Online
Ajanjakso	23/07/2021 → 23/07/2021
www-osoite	https://sites.google.com/view/udlworkshop2021

Pääsy asiakirjaan

ROSE: Robotit ja hyvinvointipalvelujen tulevaisuus
Kyrki, V. (Vastuullinen tutkija), Brander, T. (Projektin jäsen), Racca, M. (Projektin jäsen), Lundell, J. (Projektin jäsen) & Verdoja, F. (Projektin jäsen)
01/01/2018 → 30/04/2021
Projekti: Academy of Finland: Strategic research funding

Siteeraa tätä

@conference{4f2e753556e94addb686c9f787ac6393,

title = "Notes on the Behavior of MC Dropout",

abstract = "Among the various options to estimate uncertainty in deep neural networks, Monte-Carlo dropout is widely popular for its simplicity and effectiveness. However the quality of the uncertainty estimated through this method varies and choices in architecture design and in training procedures have to be carefully considered and tested to obtain satisfactory results. In this paper we present a study offering a different point of view on the behavior of Monte-Carlo dropout, which enables us to observe a few interesting properties of the technique to keep in mind when considering its use for uncertainty estimation. ",

author = "Francesco Verdoja and Ville Kyrki",

year = "2021",

month = jul,

day = "23",

language = "English",

note = "ICML Workshop on Uncertainty & Robustness in Deep Learning, ICML UDL ; Conference date: 23-07-2021 Through 23-07-2021",

url = "https://sites.google.com/view/udlworkshop2021",

}

TY - CONF

T1 - Notes on the Behavior of MC Dropout

AU - Verdoja, Francesco

AU - Kyrki, Ville

N1 - Conference code: 2021

PY - 2021/7/23

Y1 - 2021/7/23

N2 - Among the various options to estimate uncertainty in deep neural networks, Monte-Carlo dropout is widely popular for its simplicity and effectiveness. However the quality of the uncertainty estimated through this method varies and choices in architecture design and in training procedures have to be carefully considered and tested to obtain satisfactory results. In this paper we present a study offering a different point of view on the behavior of Monte-Carlo dropout, which enables us to observe a few interesting properties of the technique to keep in mind when considering its use for uncertainty estimation.

AB - Among the various options to estimate uncertainty in deep neural networks, Monte-Carlo dropout is widely popular for its simplicity and effectiveness. However the quality of the uncertainty estimated through this method varies and choices in architecture design and in training procedures have to be carefully considered and tested to obtain satisfactory results. In this paper we present a study offering a different point of view on the behavior of Monte-Carlo dropout, which enables us to observe a few interesting properties of the technique to keep in mind when considering its use for uncertainty estimation.

M3 - Paper

T2 - ICML Workshop on Uncertainty & Robustness in Deep Learning

Y2 - 23 July 2021 through 23 July 2021

ER -

Notes on the Behavior of MC Dropout

Abstrakti

Workshop

Pääsy asiakirjaan

Sormenjälki

Projektit

ROSE: Robotit ja hyvinvointipalvelujen tulevaisuus

Siteeraa tätä