Picture for Zeyu Ning

Zeyu Ning

Benchmarking Machine Learning: How Fast Can Your Algorithms Go?

Add code
Jan 08, 2021
Zeyu Ning, Hugues Nelson Iradukunda, Qingquan Zhang, Ting Zhu
Figure 1 for Benchmarking Machine Learning: How Fast Can Your Algorithms Go?
Figure 2 for Benchmarking Machine Learning: How Fast Can Your Algorithms Go?
Figure 3 for Benchmarking Machine Learning: How Fast Can Your Algorithms Go?
Figure 4 for Benchmarking Machine Learning: How Fast Can Your Algorithms Go?

This paper is focused on evaluating the effect of some different techniques in machine learning speed-up, including vector caches, parallel execution, and so on. The following content will include some review of the previous approaches and our own experimental results.

Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

MailLeak: Obfuscation-Robust Character Extraction Using Transfer Learning

Add code
Dec 22, 2020
Wei Wang, Emily Sallenback, Zeyu Ning, Hugues Nelson Iradukunda, Wenxi Lu, Qingquan Zhang, Ting Zhu
Figure 1 for MailLeak: Obfuscation-Robust Character Extraction Using Transfer Learning
Figure 2 for MailLeak: Obfuscation-Robust Character Extraction Using Transfer Learning
Figure 3 for MailLeak: Obfuscation-Robust Character Extraction Using Transfer Learning
Figure 4 for MailLeak: Obfuscation-Robust Character Extraction Using Transfer Learning

The following work presents a new algorithm for character recognition from obfuscated images. The presented method is an example of a potential threat to current postal services. This paper both analyzes the efficiency of the given algorithm and suggests countermeasures to prevent such threats from occurring.

Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon