Skip to main content
Artificial Intelligence

Return to Question

added 7 characters in body; edited title
Source Link
nbro
nbro
  • 41.4k
  • 12
  • 115
  • 205

Why do non-linear activation functions that produce values larger than 1 or smaller than 0 work?

Can someone please point me to where I can read up on whyWhy do non-linearitieslinear activation functions that can produce values larger than 1 or smaller than 0 work?

My understanding is that neurons can only produce values between 0 and 1, and that this assumption can be used in things like cross-entropy. Are my assumptions just completely wrong?

Is there any reference that explains this?

Why do non-linear functions that produce values larger than 1 or smaller than 0 work?

Can someone please point me to where I can read up on why non-linearities that can produce values larger than 1 or smaller than 0 work?

My understanding is that neurons can only produce values between 0 and 1, and that this assumption can be used in things like cross-entropy. Are my assumptions just completely wrong?

Why do non-linear activation functions that produce values larger than 1 or smaller than 0 work?

Why do non-linear activation functions that produce values larger than 1 or smaller than 0 work?

My understanding is that neurons can only produce values between 0 and 1, and that this assumption can be used in things like cross-entropy. Are my assumptions just completely wrong?

Is there any reference that explains this?

added 5 characters in body; edited tags; edited title
Source Link
nbro
nbro
  • 41.4k
  • 12
  • 115
  • 205

Why does ReLU (and otherdo non linearities)-linear functions that produce values larger than 1 or smaller than 0 work?

Can someone please point me to where I can read up on why non linearities-linearities that can produce values larger than 1 or smaller than 0 work.?

My understanding is that neurons can only produce values between 0 and 1, and that this assumption can be used in things like cross entropy-entropy. Are my assumptions just completely wrong?

Why does ReLU (and other non linearities) work?

Can someone please point me to where I can read up on why non linearities that can produce values larger than 1 or smaller than 0 work. My understanding is that neurons can only produce values between 0 and 1 and that this assumption can be used in things like cross entropy. Are my assumptions just completely wrong?

Why do non-linear functions that produce values larger than 1 or smaller than 0 work?

Can someone please point me to where I can read up on why non-linearities that can produce values larger than 1 or smaller than 0 work?

My understanding is that neurons can only produce values between 0 and 1, and that this assumption can be used in things like cross-entropy. Are my assumptions just completely wrong?

Bumped by Community user
Source Link
Emil Wormbs
Emil Wormbs
  • 59
  • 3

Why does ReLU (and other non linearities) work?

Can someone please point me to where I can read up on why non linearities that can produce values larger than 1 or smaller than 0 work. My understanding is that neurons can only produce values between 0 and 1 and that this assumption can be used in things like cross entropy. Are my assumptions just completely wrong?