Browsing by Author "Cerutti, F."

Now showing items 1-8 of 8

Handling epistemic and aleatory uncertainties in probabilistic circuits

Cerutti, F.; Kaplan, L. M.; Kimmig, A.; Şensoy, Murat (Springer, 2022-04)

When collaborating with an AI system, we need to assess when to trust its recommendations. If we mistakenly trust it in regions where it is likely to err, catastrophic failures may occur, hence the need for Bayesian ...
Interpretability of deep learning models: a survey of results

Chakraborty, S.; Tomsett, R.; Raghavendra, R.; Harborne, D.; Alzantot, M.; Cerutti, F.; Srivastava, M.; Preece, A.; Julier, S.; Rao, R. M.; Kelley, T. D.; Braines, D.; Şensoy, Murat; Willis, C. J.; Gurram, P. (IEEE, 2018-06-26)

Deep neural networks have achieved near-human accuracy levels in various types of classification and prediction tasks including images, text, speech, and video data. However, the networks continue to be treated mostly as ...
Learning and reasoning in complex coalition information environments: a critical analysis

Cerutti, F.; Alzantot, M.; Xing, T.; Harborne, D.; Bakdash, J. Z.; Braines, D.; Chakraborty, S.; Kaplan, L.; Kimmig, A.; Preece, A.; Raghavendra, R.; Şensoy, Murat; Srivastava, M. (IEEE, 2018-09-05)

In this paper we provide a critical analysis with metrics that will inform guidelines for designing distributed systems for Collective Situational Understanding (CSU). CSU requires both collective insight - i.e., accurate ...
Privacy enforcement through policy extension

Arunkumar, S.; Srivatsa, M.; Soyluoglu, Berker; Şensoy, Murat; Cerutti, F. (IEEE, 2016)

Successful coalition operations require contributions from the coalition partners which might have hidden goals and desiderata in addition to the shared coalition goals. Therefore, there is an inevitable risk-utility ...
Probabilistic logic programming with beta-distributed random variables

Cerutti, F.; Kaplan, L.; Kimmig, A.; Şensoy, Murat (Association for the Advancement of Artificial Intelligence, 2019-07-17)

We enable aProbLog-a probabilistic logical programming approach-to reason in presence of uncertain probabilities represented as Beta-distributed random variables. We achieve the same performance of state-of-the-art algorithms ...
Subjective bayesian networks and human-in-the-loop situational understanding

Braines, D.; Thomas, A.; Kaplan, L.; Şensoy, Murat; Bakdash, J. Z.; Ivanovska, M.; Preece, A.; Cerutti, F. (Springer, 2018-03-21)

In this paper we present a methodology to exploit human-machine coalitions for situational understanding. Situational understanding refers to the ability to relate relevant information and form logical conclusions, as well ...
Uncertainty-aware deep classifiers using generative models

Şensoy, Murat; Kaplan, L.; Cerutti, F.; Saleki, Maryam (Association for the Advancement of Artificial Intelligence, 2020)

Deep neural networks are often ignorant about what they do not know and overconfident when they make uninformed predictions. Some recent approaches quantify classification uncertainty directly by training the model to ...
Uncertainty-aware situational understanding

Tomsett, R.; Kaplan, L.; Cerutti, F.; Sullivan, P.; Vente, D.; Vilamala, M. R.; Kimmig, A.; Preece, A.; Şensoy, Murat (SPIE, 2019)

Situational understanding is impossible without causal reasoning and reasoning under and about uncertainty, i.e. prob-abilistic reasoning and reasoning about the confidence in the uncertainty assessment. We therefore ...