Skip to main content

All Questions

Filter by
Sorted by
Tagged with
10 votes
4 answers
17k views

Can a perceptron with sigmoid activation function perform nonlinear classification?

Consider the perceptron as illustrated in the figure above. I know: If the activation function is linear, i.e. the first three cases, then the perceptron is equivalent to a linear classifier. ...
xmllmx's user avatar
  • 243
22 votes
3 answers
16k views

From the Perceptron rule to Gradient Descent: How are Perceptrons with a sigmoid activation function different from Logistic Regression?

Essentially, my question is that in multilayer Perceptrons, perceptrons are used with a sigmoid activation function. So that in the update rule $\hat{y}$ is calculated as $$\hat{y} = \frac{1}{1+\exp(...
user avatar
2 votes
1 answer
220 views

Would multilayer perceptrons be better than multiple regression?

I am using multiple regression to predict the future value of a time series from several other time series. Would doing this with multilayer perceptrons produce better results than multiple regression?...
HumbleOrange's user avatar
1 vote
1 answer
570 views

Bias input in neural network

Does bias input work like constant value in linear regression? and if bias input is not used then resulting boundary will always pass through origin? Thanks in advance.
Siddhesh's user avatar
  • 687
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