Matches in SemOpenAlex for { <https://semopenalex.org/work/W2978049011> ?p ?o ?g. }
- W2978049011 abstract "This paper presents tree growth algorithm framework for designing convolutional neural network architecture. Convolutional neural networks are a special class of deep neural networks that typically consist of several convolution, pooling and fully connected layers. Convolutional neural networks have proved to be a robust method for tackling various image classification tasks. One of the most important challenges from this domain is to find the network architecture that has the best performance for the specific application. The performance of the network depends on the set of hyper-parameter values such as the number of convolutional and dense layers, the number of kernels per layer and kernel size. Optimization of hyperparameters was performed by novel tree growth algorithm that belongs to the group of swarm intelligence metaheuristics. The robustness, performance and solutions quality of the proposed framework was validated against the well-known MNIST dataset. Conducted comparative analysis demonstrated that the proposed frameworks obtains promising results in this domain." @default.
- W2978049011 created "2019-10-10" @default.
- W2978049011 creator A5006488537 @default.
- W2978049011 creator A5008685555 @default.
- W2978049011 creator A5050579174 @default.
- W2978049011 creator A5064081550 @default.
- W2978049011 creator A5067245090 @default.
- W2978049011 date "2019-07-01" @default.
- W2978049011 modified "2023-10-17" @default.
- W2978049011 title "Convolutional Neural Network Architecture Design by the Tree Growth Algorithm Framework" @default.
- W2978049011 cites W1755950513 @default.
- W2978049011 cites W1934184906 @default.
- W2978049011 cites W1978232925 @default.
- W2978049011 cites W2019645756 @default.
- W2978049011 cites W2040020748 @default.
- W2978049011 cites W2097117768 @default.
- W2978049011 cites W2112796928 @default.
- W2978049011 cites W2145339207 @default.
- W2978049011 cites W2157745054 @default.
- W2978049011 cites W2160815625 @default.
- W2978049011 cites W2194775991 @default.
- W2978049011 cites W2247605921 @default.
- W2978049011 cites W2250904038 @default.
- W2978049011 cites W2293983223 @default.
- W2978049011 cites W2481410279 @default.
- W2978049011 cites W2541451878 @default.
- W2978049011 cites W2606006859 @default.
- W2978049011 cites W2607631091 @default.
- W2978049011 cites W2610837804 @default.
- W2978049011 cites W2735728519 @default.
- W2978049011 cites W2755520760 @default.
- W2978049011 cites W2771523178 @default.
- W2978049011 cites W2776601846 @default.
- W2978049011 cites W2784157522 @default.
- W2978049011 cites W2786572054 @default.
- W2978049011 cites W2789856966 @default.
- W2978049011 cites W2796335625 @default.
- W2978049011 cites W2799991731 @default.
- W2978049011 cites W2808316254 @default.
- W2978049011 cites W2809254203 @default.
- W2978049011 cites W2889074766 @default.
- W2978049011 cites W2896230333 @default.
- W2978049011 cites W2896804239 @default.
- W2978049011 cites W2905073742 @default.
- W2978049011 cites W2963446712 @default.
- W2978049011 cites W2963658737 @default.
- W2978049011 cites W3100105995 @default.
- W2978049011 cites W2807905242 @default.
- W2978049011 doi "https://doi.org/10.1109/ijcnn.2019.8851755" @default.
- W2978049011 hasPublicationYear "2019" @default.
- W2978049011 type Work @default.
- W2978049011 sameAs 2978049011 @default.
- W2978049011 citedByCount "19" @default.
- W2978049011 countsByYear W29780490112019 @default.
- W2978049011 countsByYear W29780490112020 @default.
- W2978049011 countsByYear W29780490112021 @default.
- W2978049011 countsByYear W29780490112022 @default.
- W2978049011 countsByYear W29780490112023 @default.
- W2978049011 crossrefType "proceedings-article" @default.
- W2978049011 hasAuthorship W2978049011A5006488537 @default.
- W2978049011 hasAuthorship W2978049011A5008685555 @default.
- W2978049011 hasAuthorship W2978049011A5050579174 @default.
- W2978049011 hasAuthorship W2978049011A5064081550 @default.
- W2978049011 hasAuthorship W2978049011A5067245090 @default.
- W2978049011 hasConcept C104317684 @default.
- W2978049011 hasConcept C108583219 @default.
- W2978049011 hasConcept C11413529 @default.
- W2978049011 hasConcept C114614502 @default.
- W2978049011 hasConcept C119857082 @default.
- W2978049011 hasConcept C153180895 @default.
- W2978049011 hasConcept C154945302 @default.
- W2978049011 hasConcept C185592680 @default.
- W2978049011 hasConcept C190502265 @default.
- W2978049011 hasConcept C193415008 @default.
- W2978049011 hasConcept C33923547 @default.
- W2978049011 hasConcept C38652104 @default.
- W2978049011 hasConcept C41008148 @default.
- W2978049011 hasConcept C55493867 @default.
- W2978049011 hasConcept C63479239 @default.
- W2978049011 hasConcept C74193536 @default.
- W2978049011 hasConcept C81363708 @default.
- W2978049011 hasConcept C8642999 @default.
- W2978049011 hasConceptScore W2978049011C104317684 @default.
- W2978049011 hasConceptScore W2978049011C108583219 @default.
- W2978049011 hasConceptScore W2978049011C11413529 @default.
- W2978049011 hasConceptScore W2978049011C114614502 @default.
- W2978049011 hasConceptScore W2978049011C119857082 @default.
- W2978049011 hasConceptScore W2978049011C153180895 @default.
- W2978049011 hasConceptScore W2978049011C154945302 @default.
- W2978049011 hasConceptScore W2978049011C185592680 @default.
- W2978049011 hasConceptScore W2978049011C190502265 @default.
- W2978049011 hasConceptScore W2978049011C193415008 @default.
- W2978049011 hasConceptScore W2978049011C33923547 @default.
- W2978049011 hasConceptScore W2978049011C38652104 @default.
- W2978049011 hasConceptScore W2978049011C41008148 @default.
- W2978049011 hasConceptScore W2978049011C55493867 @default.
- W2978049011 hasConceptScore W2978049011C63479239 @default.
- W2978049011 hasConceptScore W2978049011C74193536 @default.
- W2978049011 hasConceptScore W2978049011C81363708 @default.
- W2978049011 hasConceptScore W2978049011C8642999 @default.