You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
I see lots of people stating unequivocally that the deep learning boom started with Krizhevsky et al 2012. But I see little credit given to Ciresan et al, who were winning image classification competitions in 2011 with deep convnets implemented in CUDA, trained on NVIDIA GPUs
I'm referring to the German Traffic Sign Recognition Benchmark at IJCNN 2011, and the ICDAR 2011 Chinese Handwriting Recognition Competition - refs: http://www.nlpr.ia.ac.cn/events/HRcompetition/ICDAR2011%20CHR%20Competition%20Final.pdf … - http://people.idsia.ch/~juergen/nn2012traffic.pdf …
I remember asking Dan Ciresan about his thoughts on Torch7, back in 2014 -- I was a Torch user at the time. He said, in essence, that he thought it was an unusable pile of bugs, and that he still preferred writing his own CUDA. I disagreed with his position at the time (still do)
I think the delta in improvement from 2011 to 2012 was significantly higher than in the past and that's why it caught the media attention. The Ciresan paper is still highly cited though.
His paper on segmenting neurons in cryo em data was the inspiration for my own work. I try to mention that paper every time someone asks how I got interested in deep learning.
There were (way) earlier papers on this by Sebastian Seung's group at MIT.
Is this because of a difference in code sharing? IIRC, it was easier to find code to reproduce Krizhevsky et al (esp. with cuda-convnet being available).
I agree. But they refused to share their code, which limited the usefulness in practice
functional history!
Convnets on GPU predate CUDA: https://hal.inria.fr/inria-00112631/document …
Which is the bigger breakthrough, fast convnets on GPU, or the knowledge that they can win hotly contested image classification competitions?
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
