Deep Learning For Automatic Visual Classification – Stefan Carlsson

Systems for of automatically classifying visual content in images has improved substantially in the last 2-3 years due to the introduction of methods of “deep learning”. This is based on training a computational network using large sets of labeled image data, i.e. where the content of the image has been annotated manually. I will speak about this and possible future developments in vision and other fields.

Discussion Points:

– Why is there a breakthrough in AI right now?

– What is the main idea with deep learning and why does it work?

– What will happen in the future?

Add comment

Highlight option

Turn on the "highlight" option for any widget, to get an alternative styling like this. You can change the colors for highlighted widgets in the theme options. See more examples below.


Instagram has returned empty data. Please authorize your Instagram account in the plugin settings .

Ivana Kotorchevikj

Categories count color


Small ads


  • Matty
  • on rear
  • Traffic lights
  • WoMo
  • Setra presentation
  • endless
  • stand still screening-smoking girl
  • Maya d'Odessa performs her art of make-up
  • Afro-deko-mono

Social Widget

Collaboratively harness market-driven processes whereas resource-leveling internal or "organic" sources.