scholarly journals An efficient test method for noise robustness of deep neural networks

2019 ◽  
Vol 10 (2) ◽  
pp. 221-235
Author(s):  
Muneki Yasuda ◽  
Hironori Sakata ◽  
Seung-Il Cho ◽  
Tomochika Harada ◽  
Atushi Tanaka ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Test Method ◽  
Noise Robustness ◽  
Efficient Test

scholarly journals Analyzing the Noise Robustness of Deep Neural Networks

2020 ◽  
pp. 1-1 ◽  
Author(s):  
Kelei Cao ◽  
Mengchen Liu ◽  
Hang Su ◽  
Jing Wu ◽  
Jun Zhu ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Noise Robustness

scholarly journals Noise-trained deep neural networks effectively predict human vision and its neural responses to challenging images

PLoS Biology ◽  
2021 ◽  
Vol 19 (12) ◽  
pp. e3001418
Author(s):  
Hojin Jang ◽  
Devin McCormack ◽  
Frank Tong
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Functional Neuroimaging ◽  
Visual Learning ◽  
Human Vision ◽  
Noise Robustness ◽  
Training Procedure ◽  
Correlated Noise ◽  
Neural Responses ◽  
Viable Model

Deep neural networks (DNNs) for object classification have been argued to provide the most promising model of the visual system, accompanied by claims that they have attained or even surpassed human-level performance. Here, we evaluated whether DNNs provide a viable model of human vision when tested with challenging noisy images of objects, sometimes presented at the very limits of visibility. We show that popular state-of-the-art DNNs perform in a qualitatively different manner than humans—they are unusually susceptible to spatially uncorrelated white noise and less impaired by spatially correlated noise. We implemented a noise training procedure to determine whether noise-trained DNNs exhibit more robust responses that better match human behavioral and neural performance. We found that noise-trained DNNs provide a better qualitative match to human performance; moreover, they reliably predict human recognition thresholds on an image-by-image basis. Functional neuroimaging revealed that noise-trained DNNs provide a better correspondence to the pattern-specific neural representations found in both early visual areas and high-level object areas. A layer-specific analysis of the DNNs indicated that noise training led to broad-ranging modifications throughout the network, with greater benefits of noise robustness accruing in progressively higher layers. Our findings demonstrate that noise-trained DNNs provide a viable model to account for human behavioral and neural responses to objects in challenging noisy viewing conditions. Further, they suggest that robustness to noise may be acquired through a process of visual learning.

Deep neural networks trained with heavier data augmentation learn features closer to representations in hIT

2018 ◽  
Author(s):  
Alex Hernández-García ◽  
Johannes Mehrer ◽  
Nikolaus Kriegeskorte ◽  
Peter König ◽  
Tim C. Kietzmann
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Data Augmentation

Representation of adversarial images in deep neural networks and the human brain

2018 ◽  
Author(s):  
Chi Zhang ◽  
Xiaohan Duan ◽  
Ruyuan Zhang ◽  
Li Tong
Keyword(s):  
Neural Networks ◽  
Human Brain ◽  
Deep Neural Networks
Sign in / Sign up

Export Citation Format

Share Document