Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034042817> ?p ?o ?g. }
- W3034042817 abstract "Designing resource-efficient Deep Neural Networks (DNNs) is critical to deploy deep learning solutions over edge platforms due to diverse performance, power, and memory budgets. Unfortunately, it is often the case a well-trained ML model does not fit to the constraint of deploying edge platforms, causing a long iteration of model reduction and retraining process. Moreover, a ML model optimized for platform-A often may not be suitable when we deploy it on another platform-B, causing another iteration of model retraining. We propose a conditional neural architecture search method using GAN, which produces feasible ML models for different platforms. We present a new workflow to generate constraint-optimized DNN models. This is the first work of bringing in condition and adversarial technique into Neural Architecture Search domain. We verify the method with regression problems and classification on CIFAR-10. The proposed workflow can successfully generate resource-optimized MLP or CNN-based networks." @default.
- W3034042817 created "2020-06-12" @default.
- W3034042817 creator A5021206737 @default.
- W3034042817 creator A5034089074 @default.
- W3034042817 creator A5035130804 @default.
- W3034042817 creator A5059251464 @default.
- W3034042817 date "2020-06-06" @default.
- W3034042817 modified "2023-09-27" @default.
- W3034042817 title "Conditional Neural Architecture Search." @default.
- W3034042817 cites W1594170634 @default.
- W3034042817 cites W1738019091 @default.
- W3034042817 cites W1825672851 @default.
- W3034042817 cites W2067523571 @default.
- W3034042817 cites W2099471712 @default.
- W3034042817 cites W2125389028 @default.
- W3034042817 cites W2173248099 @default.
- W3034042817 cites W2194775991 @default.
- W3034042817 cites W2279098554 @default.
- W3034042817 cites W2289252105 @default.
- W3034042817 cites W2300242332 @default.
- W3034042817 cites W2412510955 @default.
- W3034042817 cites W2469490737 @default.
- W3034042817 cites W2548275288 @default.
- W3034042817 cites W2593245696 @default.
- W3034042817 cites W2606722458 @default.
- W3034042817 cites W2777406049 @default.
- W3034042817 cites W2778749116 @default.
- W3034042817 cites W2786771851 @default.
- W3034042817 cites W2805939769 @default.
- W3034042817 cites W2809624076 @default.
- W3034042817 cites W2810271953 @default.
- W3034042817 cites W2883861033 @default.
- W3034042817 cites W2886851211 @default.
- W3034042817 cites W2890557332 @default.
- W3034042817 cites W2891158090 @default.
- W3034042817 cites W2906697496 @default.
- W3034042817 cites W2912997768 @default.
- W3034042817 cites W2946948417 @default.
- W3034042817 cites W2951104886 @default.
- W3034042817 cites W2952432176 @default.
- W3034042817 cites W2962690307 @default.
- W3034042817 cites W2962750597 @default.
- W3034042817 cites W2962851801 @default.
- W3034042817 cites W2962861284 @default.
- W3034042817 cites W2963114950 @default.
- W3034042817 cites W2963125010 @default.
- W3034042817 cites W2963163009 @default.
- W3034042817 cites W2963226019 @default.
- W3034042817 cites W2963374099 @default.
- W3034042817 cites W2963480671 @default.
- W3034042817 cites W2963636093 @default.
- W3034042817 cites W2963918968 @default.
- W3034042817 cites W2964081807 @default.
- W3034042817 cites W2964259004 @default.
- W3034042817 cites W2964268978 @default.
- W3034042817 cites W2964299589 @default.
- W3034042817 cites W2982479999 @default.
- W3034042817 cites W2998732502 @default.
- W3034042817 cites W3022644913 @default.
- W3034042817 hasPublicationYear "2020" @default.
- W3034042817 type Work @default.
- W3034042817 sameAs 3034042817 @default.
- W3034042817 citedByCount "0" @default.
- W3034042817 crossrefType "posted-content" @default.
- W3034042817 hasAuthorship W3034042817A5021206737 @default.
- W3034042817 hasAuthorship W3034042817A5034089074 @default.
- W3034042817 hasAuthorship W3034042817A5035130804 @default.
- W3034042817 hasAuthorship W3034042817A5059251464 @default.
- W3034042817 hasConcept C108583219 @default.
- W3034042817 hasConcept C111919701 @default.
- W3034042817 hasConcept C119857082 @default.
- W3034042817 hasConcept C123657996 @default.
- W3034042817 hasConcept C127413603 @default.
- W3034042817 hasConcept C134306372 @default.
- W3034042817 hasConcept C142362112 @default.
- W3034042817 hasConcept C153349607 @default.
- W3034042817 hasConcept C154945302 @default.
- W3034042817 hasConcept C162307627 @default.
- W3034042817 hasConcept C177212765 @default.
- W3034042817 hasConcept C2776036281 @default.
- W3034042817 hasConcept C2984842247 @default.
- W3034042817 hasConcept C33923547 @default.
- W3034042817 hasConcept C36503486 @default.
- W3034042817 hasConcept C41008148 @default.
- W3034042817 hasConcept C50644808 @default.
- W3034042817 hasConcept C77088390 @default.
- W3034042817 hasConcept C78519656 @default.
- W3034042817 hasConcept C98045186 @default.
- W3034042817 hasConceptScore W3034042817C108583219 @default.
- W3034042817 hasConceptScore W3034042817C111919701 @default.
- W3034042817 hasConceptScore W3034042817C119857082 @default.
- W3034042817 hasConceptScore W3034042817C123657996 @default.
- W3034042817 hasConceptScore W3034042817C127413603 @default.
- W3034042817 hasConceptScore W3034042817C134306372 @default.
- W3034042817 hasConceptScore W3034042817C142362112 @default.
- W3034042817 hasConceptScore W3034042817C153349607 @default.
- W3034042817 hasConceptScore W3034042817C154945302 @default.
- W3034042817 hasConceptScore W3034042817C162307627 @default.
- W3034042817 hasConceptScore W3034042817C177212765 @default.
- W3034042817 hasConceptScore W3034042817C2776036281 @default.