Zobrazeno 1 - 10 of 40 pro vyhledávání: '"Haytham Assem"'
1
Akademický článek
Assessing Feature Representations for Instance-Based Cross-Domain Anomaly Detection in Cloud Services Univariate Time Series Data
Autor: Rahul Agrahari, Matthew Nicholson, Clare Conran, Haytham Assem, John D. Kelleher
Publikováno v: IoT, Vol 3, Iss 1, Pp 123-144 (2022)
In this paper, we compare and assess the efficacy of a number of time-series instance feature representations for anomaly detection. To assess whether there are statistically significant differences between different feature representations for anoma
Externí odkaz: https://doaj.org/article/d727050ade424f59b371af8a0472b898
Zobrazit plný text záznamu
2
Akademický článek
Intent Classification by the Use of Automatically Generated Knowledge Graphs
Autor: Mihael Arcan, Sampritha Manjunath, Cécile Robin, Ghanshyam Verma, Devishree Pillai, Simon Sarkar, Sourav Dutta, Haytham Assem, John P. McCrae, Paul Buitelaar
Publikováno v: Information, Vol 14, Iss 5, p 288 (2023)
Intent classification is an essential task for goal-oriented dialogue systems for automatically identifying customers’ goals. Although intent classification performs well in general settings, domain-specific user goals can still present a challenge
Externí odkaz: https://doaj.org/article/5f2817ceddc74bdd8cc6f084aa0a9c0d
Zobrazit plný text záznamu
6
Aligned Weight Regularizers for Pruning Pretrained Neural Networks
Autor: James O’ Neill, Sourav Dutta, Haytham Assem
While various avenues of research have been explored for iterative pruning, little is known what effect pruning has on zero-shot test performance and its potential implications on the choice of pruning criteria. This pruning setup is particularly imp
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7f0b3a7e407c868aea1f387fb1bd1111
http://arxiv.org/abs/2204.01385
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje