Noise increases the correspondence between artificial and human vision.
The best performing computer vision systems are based on deep neural networks (DNNs). A study in this issue of PLOS Biology shows that DNNs trained on noisy stimuli are better than standard DNNs at mirroring both human behavioral and neural visual responses.
| প্রধান লেখক: | |
|---|---|
| বিন্যাস: | প্রবন্ধ |
| ভাষা: | English |
| প্রকাশিত: |
Public Library of Science (PLoS)
2021-12-01
|
| মালা: | PLoS Biology |
| অনলাইন ব্যবহার করুন: | https://journals.plos.org/plosbiology/article/file?id=10.1371/journal.pbio.3001477&type=printable |