Month: March 2015

LET THE MACHINE LEARN EVERYTHING! The network is designed as a traditional deep ConvNet, with successions of convolutional and pooling layers, finishing with 2 fully connected layers. The succession of convolutions makes it possible to learn very diverse sets of features, by learning convolutions of convolutions of convolutions (as if we looked at, for example, the blurred embossed image of the edges of an image, but with the actual operation being learned by the system). We learn to read like that! We arrange images in our brain, we learn the characters and associate them with sounds. We practice convolutions of convolutions until we get 100% accuracy. Babies go by images, and then we rhyme with them or say words and little phrases with the images. We keep doing that over time until they train their brain to evaluate images of entire sentences; we still go on for the ones who train themselves to fast reading. Learning for Text Understanding from Scratch

Deep Learning for Text Understanding from Scratch.

by perlajulieta

Flight of the bumblebee
“Flight of the Bumblebee” is an orchestral interlude written by Nikolai Rimsky-Korsakov for his opera The Tale of Tsar Saltan, composed in 1899–1900. The piece closes Act III, Tableau 1, during which the magic Swan-Bird changes Prince Gvidon Saltanovich (the Tsar’s son) into an insect so that he can fly away to visit his father (who does not know that he is alive). Although in the opera the Swan-Bird sings during the first part of the “Flight”, her vocal line is melodically uninvolved and easily omitted; this feature, combined with the fact that the number decisively closes the scene, made easy extraction as an orchestral concerto piece possible

(Source: https://www.youtube.com/)
by perlajulieta

Combining experimental methods from biology and physics, as well as optical modelling, we have shown that panther chameleons rapidly change colour (hue) by actively tuning the photonic… Read more

by perlajulieta