no code implementations • 23 Aug 2022 • Pietro Baroni, Federico Cerutti, Massimiliano Giacomin, Lance M. Kaplan, Murat Sensoy
The sixth assessment of the international panel on climate change (IPCC) states that "cumulative net CO2 emissions over the last decade (2010-2019) are about the same size as the 11 remaining carbon budget likely to limit warming to 1. 5C (medium confidence)."
no code implementations • 13 May 2022 • Gonul Ayci, Murat Sensoy, Arzucan Özgür, Pinar Yolum
By factoring in the user's own understanding of privacy, such as risk factors or own labels, the personal assistant can personalize its recommendations per user.
1 code implementation • 22 Feb 2021 • Federico Cerutti, Lance M. Kaplan, Angelika Kimmig, Murat Sensoy
When collaborating with an AI system, we need to assess when to trust its recommendations.
no code implementations • 13 Aug 2020 • Dell Zhang, Alexander Kuhnle, Julian Richardson, Murat Sensoy
A core task in process mining is process discovery which aims to learn an accurate process model from event log data.
no code implementations • 7 Jun 2020 • Murat Sensoy, Lance Kaplan, Federico Cerutti, Maryam Saleki
Some recent approaches quantify classification uncertainty directly by training the model to output high uncertainty for the data samples close to class boundaries or from the outside of the training distribution.
no code implementations • 20 Sep 2018 • Lance Kaplan, Federico Cerutti, Murat Sensoy, Alun Preece, Paul Sullivan
This paper argues the need for research to realize uncertainty-aware artificial intelligence and machine learning (AI\&ML) systems for decision support by describing a number of motivating scenarios.
1 code implementation • 20 Sep 2018 • Federico Cerutti, Lance Kaplan, Angelika Kimmig, Murat Sensoy
We enable aProbLog---a probabilistic logical programming approach---to reason in presence of uncertain probabilities represented as Beta-distributed random variables.
10 code implementations • NeurIPS 2018 • Murat Sensoy, Lance Kaplan, Melih Kandemir
Deterministic neural nets have been shown to learn effective predictors on a wide range of machine learning problems.