Stop Memorizing: A Data-Dependent Regularization Framework for Intrinsic Pattern Learning | Zendy

Wei Zhu | Zendy; Qiang Qiu | Zendy; Bao Wang | Zendy; Jianfeng Lu | Zendy; Guillermo Sapiro | Zendy; Ingrid Daubechies | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Stop Memorizing: A Data-Dependent Regularization Framework for Intrinsic Pattern Learning

Author(s) -

Wei Zhu,

Qiang Qiu,

Bao Wang,

Jianfeng Lu,

Guillermo Sapiro,

Ingrid Daubechies

Publication year - 2019

Publication title -

siam journal on mathematics of data science

Language(s) - English

Resource type - Journals

ISSN - 2577-0187

DOI - 10.1137/19m1236886

Subject(s) - softmax function , discriminative model , regularization (linguistics) , embedding , computer science , pattern recognition (psychology) , artificial intelligence , linear subspace , deep neural networks , artificial neural network , memorization , classifier (uml) , mathematics , algorithm , machine learning , geometry , mathematics education

Deep neural networks (DNNs) typically have enough capacity to fit random data by brute force even when conventional data-dependent regularizations focusing on the geometry of the features are impos...

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research