News for hackers. Stuff that matters.

A comment on A Quick Look at Support Vector Machines. Parent comment

Re:A Quick Look at Support Vector Machines by argonaut on Thursday March 23, 2017 @05:45PM (#13944649)
Rosenblatt's perceptron has little to do with neural nets. Geoffrey Hinton regrets coining the name "multi-layer perceptron" precisely because they're really unrelated.
[ Parent | on HN ]
Re:A Quick Look at Support Vector Machines by radarsat1 on Thursday March 23, 2017 @07:10PM (#13945191)
Hm, yeah I suppose you could argue it's not really a neural network unless you involve the idea of hidden layers. And according to wikipedia backpropagation wasn't a thing until 1975 so you might have a point.
[ Parent | on HN ]
Re:A Quick Look at Support Vector Machines by argonaut on Thursday March 23, 2017 @08:42PM (#13945641)
"It's not really a neural network" is an understatement. Perceptrons are about as related to neural nets as linear regression is (note that you can "train" linear regression with stochastic gradient descent).
[ Parent | on HN ]