Michele Caprio

Dr. Michele Caprio

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 May 2025
Verified
Conference Paper
Open access
SDSouradeep Dutta
Souradeep Dutta
MCMichele Caprio
Michele Caprio
VLVivian Lin
Vivian Lin
MCMatthew Cleaveland
Matthew Cleaveland
KJKuk Jin Jang
Kuk Jin Jang
ILInsup Lee
Insup Lee

24 April 2024
Verified
Book Chapter
Closed access
PDF file
MCMichele Caprio
Michele Caprio
YSYusuf Sale
Yusuf Sale
EHEyke Hüllermeier
Eyke Hüllermeier
ILInsup Lee
Insup Lee

18 April 2023 in IEEE Access
Verified
Journal Article
Open access
MCMichele Caprio
Michele Caprio
SMSayan Mukherjee
Sayan Mukherjee
We state concentration inequalities for the output of the hidden layers of a stochastic deep neural network (SDNN), as well as for the output of the whole SDNN. These results allow us to introduce an expected classifier (EC), and to give probabilistic upper bound for the classification error of the EC. We also state the optimal number of layers for the SDNN via an optimal stopping procedure. We apply our analysis to a stochastic version of a feedforward neural network with ReLU activation function.

31 December 2022 in Involve, a Journal of Mathematics
Verified
Journal Article
Closed access
PDF file
MCMichele Caprio
Michele Caprio
AAAndrea Aveni
Andrea Aveni
SMSayan Mukherjee
Sayan Mukherjee

14 March 2022 in Proceedings
Verified
Conference Paper
Open access
PDF file
MCMichele Caprio
Michele Caprio
AAAndrea Aveni
Andrea Aveni
SMSayan Mukherjee
Sayan Mukherjee
We present two classes of abstract prearithmetics, {AM}M≥1 and {BM}M>0. The first one is weakly projective with respect to the nonnegative real Diophantine arithmetic R+=(R+,+,×,≤R+), and the second one is projective with respect to the extended real Diophantine arithmetic R¯=(R¯,+,×,≤R¯). In addition, we have that every AM and every BM is a complete totally ordered semiring. We show that the projection of any series of elements of R+ converges in AM, for any M≥1, and that the projection of any non-indeterminate series of elements of R converges in BM, for all M>0. We also prove that working in AM, for any M≥1, and in BM, for all M>0, allows to overcome a version of the paradox of the heap.

26 October 2022 in arXiv
Verified
Preprint
Open access
PDF file
MCMichele Caprio
Michele Caprio
SMSayan Mukherjee
Sayan Mukherjee
We formulate an ergodic theory for the (almost sure) limit $\mathcal{P}^\text{co}_{\tilde{\mathcal{E}}}$ of a sequence $(\mathcal{P}^\text{co}_{\mathcal{E}_n})$ of successive dynamic imprecise probability kinematics (DIPK, introduced in Caprio and Gong, 2021) updates of a set $\mathcal{P}^\text{co}_{\mathcal{E}_0}$ representing the initial beliefs of an agent. As a consequence, we formulate a strong law of large numbers.