Bitcoin Forum
July 14, 2024, 11:50:35 AM *
News: Latest Bitcoin Core release: 27.0 [Torrent]
 
   Home   Help Search Login Register More  
Pages: [1]
  Print  
Author Topic: Machine learning: Why are NN's considered black boxes?  (Read 213 times)
This is a self-moderated topic. If you do not want to be moderated by the person who started this topic, create a new topic.
Bitcoinmeetups.org (OP)
Hero Member
*****
Offline Offline

Activity: 976
Merit: 1002


Bitcoinmeetups.org


View Profile WWW
September 09, 2017, 12:42:04 PM
 #1

Machine learning: Why are NN's considered black boxes?

I don't get it. In what senses are NN's black boxes?

(NN means neural network).

Is it really not possible to check what single nodes are doing and why a single node's weight can have such a final impact on the output of the NN?

Bmeet

Bitcoinmeetups.org: Writing, Blockchain and AI Project Development.
Telegram: Apply to join us here: https://t.me/joinchat/KU7ltBBaG59499AJ0Az4nw
Web: http://www.bitcoinmeetups.org
Pages: [1]
  Print  
 
Jump to:  

Powered by MySQL Powered by PHP Powered by SMF 1.1.19 | SMF © 2006-2009, Simple Machines Valid XHTML 1.0! Valid CSS!