Understanding generalization and optimization performance of deep CNNs
This work aims to provide understandings on the remarkable success of deep convolutional neural networks (CNNs) by theoretically analyzing their generalization performance and establishing optimization guarantees for gradient descent based training algorithms. Specifically, for a CNN model consistin...
محفوظ في:
المؤلفون الرئيسيون: | ZHOU, Pan, FENG, Jiashi |
---|---|
التنسيق: | text |
اللغة: | English |
منشور في: |
Institutional Knowledge at Singapore Management University
2018
|
الموضوعات: | |
الوصول للمادة أونلاين: | https://ink.library.smu.edu.sg/sis_research/9010 https://ink.library.smu.edu.sg/context/sis_research/article/10013/viewcontent/2018_ICML_deepCNNs.pdf |
الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
المؤسسة: | Singapore Management University |
اللغة: | English |
مواد مشابهة
-
Empirical risk landscape analysis for understanding deep neural networks
بواسطة: ZHOU, Pan, وآخرون
منشور في: (2018) -
Towards understanding why Lookahead generalizes better than SGD and beyond
بواسطة: ZHOU, Pan, وآخرون
منشور في: (2021) -
Efficient stochastic gradient hard thresholding
بواسطة: ZHOU, Pan, وآخرون
منشور في: (2018) -
Faster first-order methods for stochastic non-convex optimization on Riemannian manifolds
بواسطة: ZHOU, Pan, وآخرون
منشور في: (2019) -
Optimizing AR PAM image enhancement: learning & model based approaches with GANs & deep CNNs
بواسطة: Liu, Chenyang
منشور في: (2024)