No joke ! Artificial Intelligence is here to stay.
Kristen Stewart, as Director of Come Swim, approved the use of Artificial Intelligence in the creation of her new movie.
The released article, signed by Kristen Stewart is incredible “to get us to the needed level of quality … we chose to use GPU instances on Amazon EC2.”
The article is a perfect match for Artificial Intelligence of 2017 and we are glad that a Holywood Super Star
approved the budget for it and then endorse the results.
Read the full story here
“Bringing Impressionism to Life with Neural Style Transfer in Come Swim”
Original technical article (PDF download)
Hollywood has used the concept of artificial intelligence in films for decades. Now, one A-lister is trying to use AI to make art, instead of just inspire it.
Quartz article about this
Forbes article about this
What is inside Artificial Intelligence brain ?
Thees are some images that I took while using Deep Learning with Tensorflow
while he was trying to learn images, like the ones below.
using a lot of GPU power and tons of iterations (see below the learning process snapshots at various moments in time)
Snapshot of Artificial Intelligence neurons (activation level for pattern detection). Now I understood why is hard to catch a fly :-). Only the ones with top activation neurons survived
Kristen Stewart Article’s References and GitHub links (Tensorflow projects – super nice list – Enjoy !)
ABADI, M., AND ET AL, A. A. 2016. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. CoRR abs/1603.04467.
ATHALYE, A., 2015. Neural style.
https://github.com/anishathalye/neural-style. commit 4bfb9efb1f0e955922889187727e33185e97d934.
BAHRAMPOUR, S., RAMAKRISHNAN, N., SCHOTT, L., AND SHAH, M. 2015. Comparative study of caffe, neon, theano, and torch for deep learning. CoRR abs/1511.06435.
DUMOULIN, V., SHLENS, J., AND KUDLUR, M. 2016. A learned representation for artistic style. CoRR abs/1610.07629.
GATYS, L. A., ECKER, A. S., AND BETHGE, M. 2015. A neural algorithm of artistic style. CoRR abs/1508.06576.
JIA, Y., SHELHAMER, E., DONAHUE, J., KARAYEV, S., LONG, J., GIRSHICK, R., GUADARRAMA, S., AND DARRELL, T.2014. Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093.
JOHNSON, J., 2015. neural-style. https://github.com/jcjohnson/neural-style.
LI, Y., WANG, N., LIU, J., AND HOU, X. 2017. Demystifying Neural Style Transfer. ArXiv e-prints (Jan.).
LIU, F., 2016. style-transfer. https://github.com/fzliu/style-transfer.
RUDER, M., DOSOVITSKIY, A., AND BROX, T. 2016. Artistic Style Transfer for Videos. Springer International Publishing, Cham, 26–36.
SIMONYAN, K., AND ZISSERMAN, A. 2014. Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556.
SZEGEDY, C., LIU, W., JIA, Y., SERMANET, P., REED, S.,ANGUELOV, D., ERHAN, D., VANHOUCKE, V., AND RABINOVICH,A. 2015. Going deeper with convolutions. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1–9.
ULYANOV, D., LEBEDEV, V., VEDALDI, A., AND LEMPITSKY, V. 2016. Texture networks: Feed-forward synthesis of textures and stylized images. In International Conference on Machine Learning (ICML).
The Gost of Montepulciano
This picture was made using Artficial Intelligence by Google Photo Assistant while I was visiting this city
Artificial Intelligence identified an interesting picture on an old HD. More to come. (hint Donald J. Trump)
read more on secret code “Artificial Intelligence” on the following mobile apps or on your Apple Watch