no code implementations • 19 Jun 2021 • Francesco A. N. Palmieri, Krishna R. Pattipati, Giovanni Di Gennaro, Giovanni Fioretti, Francesco Verolla, Amedeo Buonanno
Even if path planning can be solved using standard techniques from dynamic programming and control, the problem can also be approached using probabilistic inference.
no code implementations • 5 Mar 2020 • Francesco A. N. Palmieri, Krishna R. Pattipati, Giovanni Fioretti, Giovanni Di Gennaro, Amedeo Buonanno
In this paper, probability propagation is applied to model agent's motion in potentially complex scenarios that include goals and obstacles.
1 code implementation • 25 Jan 2020 • Giovanni Di Gennaro, Amedeo Buonanno, Antonio Di Girolamo, Armando Ospedale, Francesco A. N. Palmieri
Question-answering (QA) is certainly the best known and probably also one of the most complex problem within Natural Language Processing (NLP) and artificial intelligence (AI).
no code implementations • 25 Jan 2020 • Giovanni Di Gennaro, Amedeo Buonanno, Antonio Di Girolamo, Armando Ospedale, Francesco A. N. Palmieri, Gianfranco Fedele
Word representation is fundamental in NLP tasks, because it is precisely from the coding of semantic closeness between words that it is possible to think of teaching a machine to understand text.
1 code implementation • 18 Jan 2019 • Giovanni Di Gennaro, Amedeo Buonanno, Francesco A. N. Palmieri
Bayesian networks in their Factor Graph Reduced Normal Form (FGrn) are a powerful paradigm for implementing inference graphs.
no code implementations • 7 Apr 2016 • Pasquale Coscia, Francesco A. N. Palmieri, Francesco Castaldo, Alberto Cavallo
We present a novel appearance-based approach for pose estimation of a human hand using the point clouds provided by the low-cost Microsoft Kinect sensor.
no code implementations • 26 May 2015 • Francesco A. N. Palmieri, Amedeo Buonanno
We apply belief propagation to a Bayesian bipartite graph composed of discrete independent hidden variables and discrete visible variables.
no code implementations • 16 Feb 2015 • Amedeo Buonanno, Francesco A. N. Palmieri
We propose a Multi-Layer Network based on the Bayesian framework of the Factor Graphs in Reduced Normal Form (FGrn) applied to a two-dimensional lattice.
no code implementations • 26 Aug 2013 • Francesco A. N. Palmieri
A Bayesian factor graph reduced to normal form consists in the interconnection of diverter units (or equal constraint units) and Single-Input/Single-Output (SISO) blocks.