Early Exit Strategies for Learning-to-Rank Cascades

Autor: Francesco Busolin, Claudio Lucchese, Franco Maria Nardini, Salvatore Orlando, Raffaele Perego, Salvatore Trani

Publikováno v: IEEE Access, Vol 11, Pp 126691-126704 (2023)

The ranking pipelines of modern search platforms commonly exploit complex machine-learned models and have a significant impact on the query response time. In this paper, we discuss several techniques to speed up the document scoring process based on

Externí odkaz: https://doaj.org/article/e3b25de9f0424526ae61793a43ff02df

RICH: Research and Innovation for Cultural Heritage

Autor: Vincenzo Barone, Daniele Licari, Franco Maria Nardini

Publikováno v: Conservation Science in Cultural Heritage, Vol 12, Iss 1, Pp 109-133 (2012)

This paper describes RICH: a new architecture conceived and developed at the Scuola Normale Superiore, for collecting, promoting and sharing cultural heritage data. Starting with the observation that cultural heritage is a cross-cutting field of rese

Externí odkaz: https://doaj.org/article/44a7300a32714dd98feec844ed4f08c7

On Learning Prediction Models for Tourists Paths

Autor: Ranieri Baraglia, Fabrizio Silvestri, Cristina Ioana Muntean, Franco Maria Nardini

Publikováno v: ACM transactions on intelligent systems and technology
7 (2015): 8–35. doi:10.1145/2766459
info:cnr-pdr/source/autori:Muntean C.I.; Nardini F.M.; Silvestri F.; Baraglia R./titolo:On learning prediction models for tourists paths/doi:10.1145%2F2766459/rivista:ACM transactions on intelligent systems and technology (Print)/anno:2015/pagina_da:8/pagina_a:35/intervallo_pagine:8–35/volume:7

In this article, we tackle the problem of predicting the “next” geographical position of a tourist, given her history (i.e., the prediction is done accordingly to the tourist’s current trail) by means of supervised learning techniques, namely G

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4888e150ff6c37950f10f3596b063bab
https://zenodo.org/record/8128600

Efficient traversal of decision tree ensembles with FPGAs

Autor: Veronica Gil-Costa, Fernando Loor, Salvatore Trani, Franco Maria Nardini, Romina Soledad Molina, Raffaele Perego

Publikováno v: Journal of parallel and distributed computing
155 (2021): 38–49. doi:10.1016/j.jpdc.2021.04.008
info:cnr-pdr/source/autori:Molina R.; Loor F.; Gil-Costa V.; Nardini F.M.; Perego R.; Trani S./titolo:Efficient traversal of decision tree ensembles with FPGAs/doi:10.1016%2Fj.jpdc.2021.04.008/rivista:Journal of parallel and distributed computing (Print)/anno:2021/pagina_da:38/pagina_a:49/intervallo_pagine:38–49/volume:155

System-on-Chip (SoC) based Field Programmable Gate Arrays (FPGAs) provide a hardware acceleration technology that can be rapidly deployed and tuned, thus providing a flexible solution adaptable to specific design requirements and to changing demands.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4474a5ce69ea7a2daf920550cb8c747a
https://doi.org/10.1016/j.jpdc.2021.04.008

ReNeuIR: Reaching Efficiency in Neural Information Retrieval

Autor: Sebastian Bruch, Claudio Lucchese, Franco Maria Nardini

Publikováno v: SIGIR 2022-The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 3462–3465, Madrid, Spain, 11-15/07/2022

Perhaps the applied nature of information retrieval research goes some way to explain the community's rich history of evaluating machine learning models holistically, understanding that efficacy matters but so does the computational cost incurred to

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f8d2fc17f68e2c56034319e3ff03e5e3
https://doi.org/10.1145/3477495.3531704