Skip to main content

All Questions

Filter by
Sorted by
Tagged with
1 vote
0 answers
278 views

Energy based model of perceptron loss?

I was reading LeCun's tutorial paper on energy-based models of cost functions, and came upon this table. I don't understand how he got the equation for perceptron loss. Can someone clarify how that ...
msun's user avatar
  • 11
1 vote
1 answer
530 views

Neural networks: how can convex optimization produce different weights each time?

I am training a multilayer perceptron with a logistic activation function by backpropagation. The weights are not unique - each time I redo the fit, I get a different set of weights. However the ...
Count Zero's user avatar
  • 1,029
16 votes
1 answer
22k views

Clarification about Perceptron Rule vs. Gradient Descent vs. Stochastic Gradient Descent implementation

I experimented a little bit with different Perceptron implementations and want to make sure if I understand the "iterations" correctly. Rosenblatt's original perceptron rule As far as I understand, ...
user avatar