A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Estimating Optimal Depth of VGG Net with Tree-Structured Parzen Estimators
Deep convolutional neural networks (CNNs) have shown astonishingperformances in variety of fields. However, different architecturesof the networks are required for different datasets, and findingright architecture for given data has been a topic of great interest incomputer vision communities. One of the most important factors ofthe CNNs architecture is the depth of the networks, which plays asignificant role in avoiding over-fitting. Grid Search is widely usedfor estimating the depth, but it requires huge computation time. Motivatedby this, a method for finding an optimal architecture depth isintroduced, which is based on a hyper-parameter optimizer calledTree-Structured Parzen Estimators (TPE). In this work, we showthat the TPE is capable of estimating the CNNs architecture depthwith an accuracy of 83.33% with CIFAR-10 dataset and 60.00%with CIFAR-100 dataset while it reduces the computation time bymore 70% compared to the Grid Search.
Estimating Optimal Depth of VGG Net with Tree-Structured Parzen Estimators
Deep convolutional neural networks (CNNs) have shown astonishingperformances in variety of fields. However, different architecturesof the networks are required for different datasets, and findingright architecture for given data has been a topic of great interest incomputer vision communities. One of the most important factors ofthe CNNs architecture is the depth of the networks, which plays asignificant role in avoiding over-fitting. Grid Search is widely usedfor estimating the depth, but it requires huge computation time. Motivatedby this, a method for finding an optimal architecture depth isintroduced, which is based on a hyper-parameter optimizer calledTree-Structured Parzen Estimators (TPE). In this work, we showthat the TPE is capable of estimating the CNNs architecture depthwith an accuracy of 83.33% with CIFAR-10 dataset and 60.00%with CIFAR-100 dataset while it reduces the computation time bymore 70% compared to the Grid Search.
Estimating Optimal Depth of VGG Net with Tree-Structured Parzen Estimators
Yoo, Sunghwan (author) / Haider, Masoom A. (author) / Khalvati, Farzad (author)
2017-10-15
doi:10.15353/vsnl.v3i1.175
Journal of Computational Vision and Imaging Systems; Vol 3 No 1 (2017) ; 2562-0444 ; 10.15353/vsnl.v3i1
Article (Journal)
Electronic Resource
English
DDC:
720
Model-based Optimisation with Tree-structured Parzen Estimation for Container Terminals
| BASE | 2019
Structural damage identification using Parzenâwindow approach and neural networks
| Wiley | 2007