FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3086094963> ?p ?o ?g. }

• W3086094963 abstract "Early advancements in convolutional neural networks (CNNs) architectures are primarily driven by human expertise and by elaborate design processes. Recently, neural architecture search was proposed with the aim of automating the network design process and generating task-dependent architectures. While existing approaches have achieved competitive performance in image classification, they are not well suited to problems where the computational budget is limited for two reasons: (1) the obtained architectures are either solely optimized for classification performance, or only for one deployment scenario; (2) the search process requires vast computational resources in most approaches. To overcome these limitations, we propose an evolutionary algorithm for searching neural architectures under multiple objectives, such as classification performance and floating-point operations (FLOPs). The proposed method addresses the first shortcoming by populating a set of architectures to approximate the entire Pareto frontier through genetic operations that recombine and modify architectural components progressively. Our approach improves computational efficiency by carefully down-scaling the architectures during the search as well as reinforcing the patterns commonly shared among past successful architectures through Bayesian model learning. The integration of these two main contributions allows an efficient design of architectures that are competitive and in most cases outperform both manually and automatically designed architectures on benchmark image classification datasets: CIFAR, ImageNet, and human chest X-ray. The flexibility provided from simultaneously obtaining multiple architecture choices for different compute requirements further differentiates our approach from other methods in the literature. Code is available at https://github.com/mikelzc1990/nsganetv1" @default.
• W3086094963 created "2020-09-21" @default.
• W3086094963 creator A5004837138 @default.
• W3086094963 creator A5027687139 @default.
• W3086094963 creator A5031717929 @default.
• W3086094963 creator A5033455019 @default.
• W3086094963 creator A5034853476 @default.
• W3086094963 creator A5068379698 @default.
• W3086094963 creator A5088394271 @default.
• W3086094963 date "2019-12-03" @default.
• W3086094963 modified "2023-10-18" @default.
• W3086094963 title "Multi-Objective Evolutionary Design of Deep Convolutional Neural Networks for Image Classification" @default.
• W3086094963 cites W157468466 @default.
• W3086094963 cites W1995861141 @default.
• W3086094963 cites W2000295051 @default.
• W3086094963 cites W2009797711 @default.
• W3086094963 cites W2071707442 @default.
• W3086094963 cites W2075742732 @default.
• W3086094963 cites W2093647425 @default.
• W3086094963 cites W2097117768 @default.
• W3086094963 cites W2102006495 @default.
• W3086094963 cites W2111935653 @default.
• W3086094963 cites W2112299196 @default.
• W3086094963 cites W2124290836 @default.
• W3086094963 cites W2126105956 @default.
• W3086094963 cites W2158591074 @default.
• W3086094963 cites W2171658832 @default.
• W3086094963 cites W2194775991 @default.
• W3086094963 cites W225560312 @default.
• W3086094963 cites W2295107390 @default.
• W3086094963 cites W2307770531 @default.
• W3086094963 cites W2335728318 @default.
• W3086094963 cites W2468462628 @default.
• W3086094963 cites W2521809336 @default.
• W3086094963 cites W2549139847 @default.
• W3086094963 cites W2556833785 @default.
• W3086094963 cites W2593744649 @default.
• W3086094963 cites W2594529350 @default.
• W3086094963 cites W2606006859 @default.
• W3086094963 cites W2614367549 @default.
• W3086094963 cites W2616257225 @default.
• W3086094963 cites W2618533983 @default.
• W3086094963 cites W2746314669 @default.
• W3086094963 cites W2750384547 @default.
• W3086094963 cites W2765312638 @default.
• W3086094963 cites W2770241596 @default.
• W3086094963 cites W2782417188 @default.
• W3086094963 cites W2796265726 @default.
• W3086094963 cites W2798405286 @default.
• W3086094963 cites W2808938483 @default.
• W3086094963 cites W2809148884 @default.
• W3086094963 cites W2810075754 @default.
• W3086094963 cites W2810271953 @default.
• W3086094963 cites W2885820039 @default.
• W3086094963 cites W2887063112 @default.
• W3086094963 cites W2897275599 @default.
• W3086094963 cites W2901579871 @default.
• W3086094963 cites W2913732044 @default.
• W3086094963 cites W2917028965 @default.
• W3086094963 cites W2953308748 @default.
• W3086094963 cites W2953937638 @default.
• W3086094963 cites W2954070046 @default.
• W3086094963 cites W2954234207 @default.
• W3086094963 cites W2955425717 @default.
• W3086094963 cites W2960010704 @default.
• W3086094963 cites W2962746461 @default.
• W3086094963 cites W2962750597 @default.
• W3086094963 cites W2962835968 @default.
• W3086094963 cites W2962847160 @default.
• W3086094963 cites W2963060032 @default.
• W3086094963 cites W2963125010 @default.
• W3086094963 cites W2963136578 @default.
• W3086094963 cites W2963137684 @default.
• W3086094963 cites W2963163009 @default.
• W3086094963 cites W2963207607 @default.
• W3086094963 cites W2963263347 @default.
• W3086094963 cites W2963374479 @default.
• W3086094963 cites W2963420686 @default.
• W3086094963 cites W2963446712 @default.
• W3086094963 cites W2963551763 @default.
• W3086094963 cites W2963778169 @default.
• W3086094963 cites W2963821229 @default.
• W3086094963 cites W2963857521 @default.
• W3086094963 cites W2963918968 @default.
• W3086094963 cites W2964081807 @default.
• W3086094963 cites W2964166963 @default.
• W3086094963 cites W2964212578 @default.
• W3086094963 cites W2964259004 @default.
• W3086094963 cites W2964331719 @default.
• W3086094963 cites W2965658867 @default.
• W3086094963 cites W2967733054 @default.
• W3086094963 cites W2981985696 @default.
• W3086094963 cites W2982083293 @default.
• W3086094963 cites W2995727387 @default.
• W3086094963 cites W3011120880 @default.
• W3086094963 cites W3101156210 @default.
• W3086094963 cites W3118608800 @default.
• W3086094963 doi "https://doi.org/10.48550/arxiv.1912.01369" @default.
• W3086094963 hasPublicationYear "2019" @default.
• W3086094963 type Work @default.

• next