Uncertainty estimation with neural network for time series data

Levente, Foldesi (2022) Uncertainty estimation with neural network for time series data. Bachelor's Thesis, Artificial Intelligence.

Preview	Text bAI_2022_LeventeFoldesi.pdf Download (2MB) | Preview
	Text toestemming.pdf Restricted to Registered users only Download (123kB)

Abstract

Nowadays, more and more high-stakes decisions are made using neural networks in order to make predictions. Specifically, meteorologists and hedge funds apply these techniques to time series data. When it comes to prediction, there are certain limitations for machine learning models (such as lack of expressiveness, vulnerability of domain shifts and overconfidence) which can be solved using uncertainty estimation. There is a set of expectations regarding how uncertainty should ``behave". For instance, a wider prediction horizon should lead to more uncertainty or the model's confidence should be proportional to its accuracy. In this paper, different uncertainty estimation methods are used in order to forecast meteorological time series data and justify these expectations. The results show how each uncertainty estimation method performs on the forecasting task and confirm the expectations of uncertainty.

Item Type:	Thesis (Bachelor's Thesis)
Supervisor name:	Valdenegro Toro, M.A.
Degree programme:	Artificial Intelligence
Thesis type:	Bachelor's Thesis
Language:	English
Date Deposited:	16 Aug 2022 09:08
Last Modified:	16 Aug 2022 09:08
URI:	https://fse.studenttheses.ub.rug.nl/id/eprint/28360

Actions (login required)

View Item