Oleg Zabluda's blog
Monday, September 12, 2016
 
Defeating Image Obfuscation with Deep Learning (2016) Richard McPherson, Reza Shokri, Vitaly Shmatikov
Defeating Image Obfuscation with Deep Learning (2016) Richard McPherson, Reza Shokri, Vitaly Shmatikov
"""
neural networks can recover hidden information from images protected by various forms of obfuscation. [...] mosaicing (also known as pixelation), blurring (as used by YouTube), and P3, a recently proposed system for privacy-preserving photo sharing that encrypts the significant JPEG coefficients to make images unrecognizable by humans. We empirically show how to train artificial neural networks to successfully identify faces and recognize objects and handwritten digits even if the images are protected using any of the above obfuscation techniques.
"""
https://arxiv.org/abs/1609.00408
https://arxiv.org/abs/1609.00408

Labels:


- posted by Oleg Zabluda @ 9:24 PM | permalink | | | technorati | bloglines | feedster
 
"""
"""
Engineers at Sydney-based Metamako LP and Exablaze Pty. Ltd., and Chicago-based xCelor LLC are rolling out switches that take around four nanoseconds—four billionths of a second—for messages to transit from one side to the other, sending data from exchanges to electronic traders.
[...]
Metamako’s devices logged a consistent speed of four nanoseconds regardless [OZ: L1] of traffic volume [...] Metamako and xCelor said they complete the entire messaging job, including the more complicated task of shooting orders back to the exchange, in around 85 nanoseconds [OZ: L2-L3]. The equivalent time for Cisco’s fastest switch is at least 240 nanoseconds, according to the company’s website.
[...]
Metamako sells about 100 ultralow-latency switches monthly [...] At around $20,000
"""
http://www.wsj.com/articles/trading-tech-accelerates-toward-speed-of-light-1470559173
http://www.wsj.com/articles/trading-tech-accelerates-toward-speed-of-light-1470559173

Labels:


- posted by Oleg Zabluda @ 11:45 AM | permalink | | | technorati | bloglines | feedster
 
AlexNet, Overfeat, VGG, GoogleNet, ResNet
AlexNet, Overfeat, VGG, GoogleNet, ResNet,
Region Based CNNs (R-CNN - 2013, Fast R-CNN - 2015, Faster R-CNN - 2015) graphics collected in one place
https://adeshpande3.github.io/The-9-Deep-Learning-Papers-You-Need-To-Know-About.html
https://adeshpande3.github.io/The-9-Deep-Learning-Papers-You-Need-To-Know-About.html

Labels:


- posted by Oleg Zabluda @ 10:38 AM | permalink | | | technorati | bloglines | feedster

Powered by Blogger