Author

Topic: Machine learning: Why are NN's considered black boxes? (Read 222 times)

hero member
Activity: 976
Merit: 1002
Bitcoinmeetups.org
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
Jump to: