Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
wiki:research [2014/10/24 19:26]
Alessandro G
wiki:research [2015/01/13 11:07] (current)
Alessandro G
Line 16: Line 16:
  
 ===== Efficient testing of Deep Neural Networks ===== ===== Efficient testing of Deep Neural Networks =====
-Convolutional Deep Neural Networks are surprisingly goodbut how to apply them quickly ​to every pixel of a large image (e.g. for segmentation/​detection)?​: here'​s ​ [[wiki:​fast_scanning|how]].+Convolutional Deep Neural Networks are surprisingly good for image segmentation and object detection tasks; ​but applying these networks ​to every patch of a large image is computationally expensive: here'​s ​our [[wiki:​fast_scanning|fast scanning]] algorithm which speeds this up by several orders of magnitude.
  
 ===== Distributed Algorithms for the Smart Grid ===== ===== Distributed Algorithms for the Smart Grid =====
-am actively involved in the swiss [[http://​www.s2g.ch|S2G]] project.+have been actively involved in the swiss [[http://​www.s2g.ch|S2G]] project ​and I am currently working on the [[http://​www.alpiq-intec.ch/​en/​energy-efficiency/​smart-technologies/​gridsense/​gridsense.jsp|GridSense]] technology.
  
 +[[wiki:​tsg|Supplementary material]] for our paper "​Restricted Neighborhood Communication Improves Decentralized Demand-Side Load Management",​ Transactions on Smart Grid, 2104.
  
 ====== Past research interests ====== ====== Past research interests ======