Matches in SemOpenAlex for { <https://semopenalex.org/work/W2989756097> ?p ?o ?g. }
- W2989756097 abstract "The recent progress in neural architecture search (NAS) has allowed scaling the automated design of neural architectures to real-world domains, such as object detection and semantic segmentation. However, one prerequisite for the application of NAS are large amounts of labeled data and compute resources. This renders its application challenging in few-shot learning scenarios, where many related tasks need to be learned, each with limited amounts of data and compute time. Thus, few-shot learning is typically done with a fixed neural architecture. To improve upon this, we propose MetaNAS, the first method which fully integrates NAS with gradient-based meta-learning. MetaNAS optimizes a meta-architecture along with the meta-weights during meta-training. During meta-testing, architectures can be adapted to a novel task with a few steps of the task optimizer, that is: task adaptation becomes computationally cheap and requires only little data per task. Moreover, MetaNAS is agnostic in that it can be used with arbitrary model-agnostic meta-learning algorithms and arbitrary gradient-based NAS methods. %We present encouraging results for MetaNAS with a combination of DARTS and REPTILE on few-shot classification benchmarks. Empirical results on standard few-shot classification benchmarks show that MetaNAS with a combination of DARTS and REPTILE yields state-of-the-art results." @default.
- W2989756097 created "2019-12-05" @default.
- W2989756097 creator A5021309471 @default.
- W2989756097 creator A5027966876 @default.
- W2989756097 creator A5031002895 @default.
- W2989756097 creator A5049054914 @default.
- W2989756097 date "2019-11-25" @default.
- W2989756097 modified "2023-09-23" @default.
- W2989756097 title "Meta-Learning of Neural Architectures for Few-Shot Learning" @default.
- W2989756097 cites W2111935653 @default.
- W2989756097 cites W2137825550 @default.
- W2989756097 cites W2194321275 @default.
- W2989756097 cites W2547875792 @default.
- W2989756097 cites W2548228487 @default.
- W2989756097 cites W2556833785 @default.
- W2989756097 cites W2593744649 @default.
- W2989756097 cites W2594529350 @default.
- W2989756097 cites W2601450892 @default.
- W2989756097 cites W2604763608 @default.
- W2989756097 cites W2752331852 @default.
- W2989756097 cites W2753160622 @default.
- W2989756097 cites W2795900505 @default.
- W2989756097 cites W2796265726 @default.
- W2989756097 cites W2809234895 @default.
- W2989756097 cites W2810075754 @default.
- W2989756097 cites W2883188678 @default.
- W2989756097 cites W2885820039 @default.
- W2989756097 cites W2891778567 @default.
- W2989756097 cites W2892366900 @default.
- W2989756097 cites W2902253437 @default.
- W2989756097 cites W2914752403 @default.
- W2989756097 cites W2936599103 @default.
- W2989756097 cites W2960010704 @default.
- W2989756097 cites W2962723986 @default.
- W2989756097 cites W2962740476 @default.
- W2989756097 cites W2962847160 @default.
- W2989756097 cites W2962919941 @default.
- W2989756097 cites W2963070905 @default.
- W2989756097 cites W2963136578 @default.
- W2989756097 cites W2963137684 @default.
- W2989756097 cites W2963303956 @default.
- W2989756097 cites W2963305465 @default.
- W2989756097 cites W2963341924 @default.
- W2989756097 cites W2963374479 @default.
- W2989756097 cites W2963423218 @default.
- W2989756097 cites W2963536136 @default.
- W2989756097 cites W2963821229 @default.
- W2989756097 cites W2964078140 @default.
- W2989756097 cites W2964081403 @default.
- W2989756097 cites W2964081807 @default.
- W2989756097 cites W2964112702 @default.
- W2989756097 cites W2964212578 @default.
- W2989756097 cites W2964259004 @default.
- W2989756097 cites W2964294659 @default.
- W2989756097 cites W2964331719 @default.
- W2989756097 cites W2978535238 @default.
- W2989756097 cites W2994653652 @default.
- W2989756097 cites W2995892679 @default.
- W2989756097 cites W2996012599 @default.
- W2989756097 cites W99485931 @default.
- W2989756097 cites W2904817185 @default.
- W2989756097 hasPublicationYear "2019" @default.
- W2989756097 type Work @default.
- W2989756097 sameAs 2989756097 @default.
- W2989756097 citedByCount "1" @default.
- W2989756097 countsByYear W29897560972021 @default.
- W2989756097 crossrefType "posted-content" @default.
- W2989756097 hasAuthorship W2989756097A5021309471 @default.
- W2989756097 hasAuthorship W2989756097A5027966876 @default.
- W2989756097 hasAuthorship W2989756097A5031002895 @default.
- W2989756097 hasAuthorship W2989756097A5049054914 @default.
- W2989756097 hasConcept C119857082 @default.
- W2989756097 hasConcept C120665830 @default.
- W2989756097 hasConcept C121332964 @default.
- W2989756097 hasConcept C123657996 @default.
- W2989756097 hasConcept C139807058 @default.
- W2989756097 hasConcept C142362112 @default.
- W2989756097 hasConcept C153349607 @default.
- W2989756097 hasConcept C154945302 @default.
- W2989756097 hasConcept C162324750 @default.
- W2989756097 hasConcept C178790620 @default.
- W2989756097 hasConcept C185592680 @default.
- W2989756097 hasConcept C187736073 @default.
- W2989756097 hasConcept C2776151529 @default.
- W2989756097 hasConcept C2778344882 @default.
- W2989756097 hasConcept C2780451532 @default.
- W2989756097 hasConcept C2781002164 @default.
- W2989756097 hasConcept C41008148 @default.
- W2989756097 hasConcept C50644808 @default.
- W2989756097 hasConcept C89600930 @default.
- W2989756097 hasConceptScore W2989756097C119857082 @default.
- W2989756097 hasConceptScore W2989756097C120665830 @default.
- W2989756097 hasConceptScore W2989756097C121332964 @default.
- W2989756097 hasConceptScore W2989756097C123657996 @default.
- W2989756097 hasConceptScore W2989756097C139807058 @default.
- W2989756097 hasConceptScore W2989756097C142362112 @default.
- W2989756097 hasConceptScore W2989756097C153349607 @default.
- W2989756097 hasConceptScore W2989756097C154945302 @default.
- W2989756097 hasConceptScore W2989756097C162324750 @default.
- W2989756097 hasConceptScore W2989756097C178790620 @default.