-
Improving Siamese Networks for One Shot Learning using Kernel Based Activation functionsARXIV/Convolution Neural Network 2020. 3. 3. 10:18
https://arxiv.org/abs/1910.09798v1
Improving Siamese Networks for One Shot Learning using Kernel Based Activation functions
The lack of a large amount of training data has always been the constraining factor in solving a lot of problems in machine learning, making One Shot Learning one of the most intriguing ideas in machine learning. It aims to learn information about object c
arxiv.org
Siamese neural networks에서 Kafnet을 사용하여 적은 epochs로 embedding 하여 정확도를 높이는 법을 제시한다. kernel 활성화 함수를 사용하여 Relu를 사용하는 딥러닝 모델보다 뛰어난 결과 얻을 수 있다.
'ARXIV > Convolution Neural Network' 카테고리의 다른 글