From colors to deep learning: a physicist playing with images

Data evento: 
Da  04/04/201704/04/2017

Giulio Alessandrini, Kernel Developer, Wolfram Research Inc., interverrà martedì 4 aprile alle ore 16 presso la Lecture Room A, edificio F del Dipartimento di Fisica in via Valerio, 2 a Trieste nell’ambito degli Alumnorum Colloquia e porterà il suo intervento su

From colors to deep learning: a physicist playing with images

Image processing has been since many years at the forefront of computer science and the recent, exciting developments in deep learning applied to computer vision aroused the interest in the field even more. However, while the old style image processing pipelines were very well understood and relied on solid mathematical arguments, the more modern neural networks often seem like a black magic solution to a badly defined problem. In this talk, I will try to shed some light on the matter, comparing old algorithms and new approaches, and show with simple examples how to build and train a network to solve a computer vision task.

Organizzazione a cura di: M. Budinich, E. Milotti, E. Vesselli

 

Download: