Surveillance-nature images are released in the download links as "sv_data.*". Download all such files, then unzip them with the same password as the web-nature data. We also conducted a fine-grained classification experiment for this part of data. The results are provided in the arXiv paper.
There is a new release of Deep Learning Book by Yoshua Bengio: http://www.iro.umontreal.ca/~bengioy/dlbook/
Do not hesitate to forward these messages to fellow data scientists
In this notebook, we cover the basics of probability theory, and show how to implement the theory in Python. (You should have a little background in probability and Python.) Then we show how to solve some particularly perplexing paradoxical probability problems.
The essential mathematics necessary for Data Science can be acquired with these 15 MOOCs, with a strong emphasis on applied algebra & statistics.
http://www.kdnuggets.com/2015/09/15-math-mooc-data-science.html
http://www.kdnuggets.com/2015/09/15-math-mooc-data-science.html
KDnuggets
15 Mathematics MOOCs for Data Science - KDnuggets
The essential mathematics necessary for Data Science can be acquired with these 15 MOOCs, with a strong emphasis on applied algebra & statistics.
"On the ImageNet dataset, our method reduced the storage required by AlexNet by 35x from 240MB to 6.9MB, without loss of accuracy. Our method reduced the size of VGG16 by 49x from 552MB to 11.3MB, again with no loss of accuracy."