Deep learning is creating computer systems we don't fully understand

Re:Deep learning is creating computer systems we don't fully... by rwallace on Wednesday July 13, 2016 @04:30PM (#12089433)

Actually, the minimal neural network that always outputs that string would basically have a weight vector equivalent to the ASCII coding of the string, so it would be equally easy to reason about compared to the Python equivalent.

[ Parent | on HN ]

Re:Deep learning is creating computer systems we don't fully... by Klockan on Thursday July 14, 2016 @02:01AM (#12091939)

You are comparing apples to oranges. The python line is a good representation of a part of a larger program, while the neural network you are talking about is not a good representation of any part of a larger neural network. You wont get that solution if you train it normally without knowing how to solve the problem yourself. Try setting up a network with 3 layers of nodes and 120 nodes in each layer and train it to output "Hello, world!" using a standard training method, you wont get something easily comprehensible from that.

[ Parent | on HN ]