Deep neural networks are lazy : on the inductive bias of deep learning
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Main Author: | Mansour, Tarek,M. Eng.Massachusetts Institute of Technology. |
---|---|
Other Authors: | Aleksander Madry. |
Format: | Thesis |
Language: | eng |
Published: |
Massachusetts Institute of Technology
2019
|
Subjects: | |
Online Access: | https://hdl.handle.net/1721.1/121680 |
Similar Items
-
Enhancing adversarial robustness of deep neural networks
by: Zhang, Jeffrey,M. Eng.Massachusetts Institute of Technology.
Published: (2019) -
Rethinking methods to train deep neural networks : contributions of distinct regimes during training
by: Wei, Wendy,M. Eng.Massachusetts Institute of Technology.
Published: (2019) -
Integrated multiparametric deep spatial phenotyping of mouse models of lung adenocarcinoma
by: Dai, Yang,M. Eng.Massachusetts Institute of Technology.
Published: (2020) -
Understanding and mitigating unintended demographic bias in machine learning systems
by: Sweeney, Christopher(Christopher J.),M. Eng.Massachusetts Institute of Technology.
Published: (2019) -
An empirical study identifying bias in Yelp dataset
by: Choi, Seri,M. Eng.Massachusetts Institute of Technology.
Published: (2021)