Novel Surrogate Measures Based on a Similarity Network for Neural Architecture Search
We propose two novel surrogate measures to predict the validation accuracy of the classification produced by a given neural architecture, thus eliminating the need to train it, in order to speed up neural architecture search (NAS). The surrogate measures
Zeki Kus, Can Akkan, Ayla Gulcu
doaj +1 more source
Effective and Efficient Similarity Search in Scientific Workflow Repositories [PDF]
International audienceScientific workflows have become a valuable tool for large-scale data processing and analysis. This has led to the creation of specialized online repositories to facilitate worflkow sharing and reuse.
Cohen-Boulakia, Sarah +4 more
core +3 more sources
SSMAL: similarity searching with alignment graphs. [PDF]
Abstract MOTIVATION: We want to provide biologists with a fast and sensitive scanning tool for searching local alignments of a protein query sequence against databases of protein multiple alignments, such as ProDom. Conversely, we want to provide a tool for locally aligning a protein multiple alignment query against a protein database ...
openaire +2 more sources
Visualising the structure of document search results: A comparison of graph theoretic approaches [PDF]
This is the post-print of the article - Copyright @ 2010 Sage PublicationsPrevious work has shown that distance-similarity visualisation or ‘spatialisation’ can provide a potentially useful context in which to browse the results of a query search ...
Busing F. +7 more
core +1 more source
KnowIME: A System to Construct a Knowledge Graph for Intelligent Manufacturing Equipment
With the development of a new generation of information technology, such as big data and cognitive intelligence, we are in the postmodern era of artificial intelligence.
Hehua Yan, Jun Yang, Jiafu Wan
doaj +1 more source
Template matching via bipartite graph and graph attention mechanism
Most existing template matching algorithms are global matching between the template target and the search region, which makes the matching process retain a lot of unfavourable background information and ignore the structure and local information of the ...
Kai Zhao, Binbing He, Wei Lei, Yuan Zhu
doaj +1 more source
Optimal sub-arraying of compromise planar arrays through an innovative ACO-weighted procedure [PDF]
In this paper, the synthesis of sub-arrayed monopulse planar arrays providing an optimal sum pattern and best compromise difference patterns is addressed by means of an innovative clustering approach based on the Ant Colony Optimizer.
Oliveri, Giacomo, Poli, Lorenzo
core +1 more source
Graph4Med: a web application and a graph database for visualizing and analyzing medical databases
Background Medical databases normally contain large amounts of data in a variety of forms. Although they grant significant insights into diagnosis and treatment, implementing data exploration into current medical databases is challenging since these are ...
Jero Schäfer +4 more
doaj +1 more source
MinoanER: Schema-Agnostic, Non-Iterative, Massively Parallel Resolution of Web Entities [PDF]
Entity Resolution (ER) aims to identify different descriptions in various Knowledge Bases (KBs) that refer to the same entity. ER is challenged by the Variety, Volume and Veracity of entity descriptions published in the Web of Data.
Christophides, Vassilis +3 more
core +2 more sources
Vessel Trajectory Similarity Computation Based on Heterogeneous Graph Neural Network
As AIS data play an increasingly important role in intelligent shipping and shipping regulation, research on AIS trajectories has attracted more attention. Effective measurement is a critical issue in AIS trajectory research.
Sizhe Luo, Weiming Zeng
doaj +1 more source

