Sigmoid for regression

Question

i just started with data-science, so if this is a very dumb question then please excuse me... So, i just learnt about the sigmoid neuron, and learnt that its range is [0, 1]. The question i have is that how can it be used in regression tasks, for example to predict the cost of any real estate property, or the imdb rating of a movie, or something I am aware of the scaling method (multiplying the output of sigmoid with any number) to get real outputs, but that works only for outputs which have an upper limit, like the imdb rating, what about stuff like the price of a commodity or something?

Thanks in advance

score 1 · Accepted Answer · answered Mar 27 '20 at 06:27

1

In Regression tasks, The output layer of the Neural Net. shouldn't be Sigmoid function. You should use a function that does not have limits in its range. Sigmoid function often used in the middle layers of a Neural net.

You can use a Linear function or a Relu (Rectified Linear Unit) for Regression tasks.

Ps: Remember that Logistic regression is an algorithm for Classification in contrast to its name. Make sure you don't mix them up.

answered Mar 27 '20 at 06:27

Amin Taheri

74
4

1

oh, i get it, thanks for the clarification, and i'lll make sure not to confuse those terms in the future... Thanks again – DS3a Mar 27 '20 at 10:02
It's my pleasure. – Amin Taheri Mar 27 '20 at 15:51

Sigmoid for regression

1 Answers1