Timeline for How to choose neural network architecture for a relatively small dataset with less than 10 features for regression?
Current License: CC BY-SA 4.0
12 events
when toggle format | what | by | license | comment | |
---|---|---|---|---|---|
Nov 24, 2022 at 21:45 | answer | added | noe | timeline score: 1 | |
Nov 24, 2022 at 20:35 | history | edited | Ethan | CC BY-SA 4.0 |
deleted 2 characters in body
|
Nov 24, 2022 at 20:06 | comment | added | Dave | I would advise against a neural network of any kind. Why do you want to use a neural network? | |
Nov 24, 2022 at 20:02 | comment | added | user17420392 | Any tips/advice how to proceed with the architecture due to the constrained dataset size ? | |
Nov 24, 2022 at 20:01 | comment | added | user17420392 | I will explore other activations functions as well. Thank you | |
Nov 24, 2022 at 20:00 | comment | added | Dave | That’s a good way to think of it, but that works for any activation function, not just ReLU. | |
Nov 24, 2022 at 19:58 | comment | added | user17420392 | Yes, that was kind of my intuition. Like a stacked linear regression model | |
Nov 24, 2022 at 19:56 | comment | added | Dave | Do you mean that the neural network acts like a linear regression on the final hidden layer? | |
Nov 24, 2022 at 19:54 | comment | added | user17420392 | I thought of it like this : in linear regression we find ideal coefficients for each attribute, in a polynomial sense) at least, so the network weights act as coefficients and relu inside a neurons helps in computing the dot product of the weights with the input and passes it on | |
Nov 24, 2022 at 19:48 | comment | added | Dave | How do you figure that ReLU is a form of linear regression? // I don’t think $80$ points is enough to do any serious work with a neural network, anyway. If you just want to learn the mechanics of coding up your model, though, then that is fine. | |
S Nov 24, 2022 at 19:44 | review | First questions | |||
Nov 25, 2022 at 7:39 | |||||
S Nov 24, 2022 at 19:44 | history | asked | user17420392 | CC BY-SA 4.0 |