Skip to main content
Became Hot Network Question
added 3 characters in body; edited tags; edited title
Source Link
nbro
  • 41.4k
  • 12
  • 115
  • 205

Activation Why is the derivative of the activation functions in neural networks important?

I'm new to NN, and. I am trying to understand some of its foundations. One question that I have is, why the derivative of an activation function is important: (not the function itselt), and why it's the derivative which is tied to how the network performs learningwhy the derivative of an activation function is important (not the function itself), and why it's the derivative which is tied to how the network performs learning?

For instance, when we say a constant derivative isn't good for learning, what is the intuition behind that? Is the activation function somehow like a hash function that needs to well differentiate small variance in inputs?

Activation functions in neural networks

I'm new to NN, and trying to understand some of its foundations. One question that I have is, why the derivative of an activation function is important (not the function itselt), and why it's the derivative which is tied to how the network performs learning?

For instance, when we say a constant derivative isn't good for learning, what is the intuition behind that? Is the activation function somehow like a hash function that needs to well differentiate small variance in inputs?

Why is the derivative of the activation functions in neural networks important?

I'm new to NN. I am trying to understand some of its foundations. One question that I have is: why the derivative of an activation function is important (not the function itself), and why it's the derivative which is tied to how the network performs learning?

For instance, when we say a constant derivative isn't good for learning, what is the intuition behind that? Is the activation function somehow like a hash function that needs to well differentiate small variance in inputs?

added 1 character in body
Source Link
Mary
  • 983
  • 6
  • 13

I'm new to NN, and trying to understand thesome of its foundations. One question that I have is, why the derivative of an activation function is important (not the function itselt), and why it's the derivative which is tied to how the network performs learning?

For instance, when we say a constant derivative isn't good for learning. What, what is the intuition behind that? Is the activation function somehow like a hash function that needneeds to well differentiate small variance in inputs?

I'm new to NN, and trying to understand the foundations. One question that I have is, why the derivative of an activation function is important, and is tied to how the network performs learning?

For instance, when we say a constant derivative isn't good for learning. What is the intuition behind that? Is the activation function somehow like a hash function that need to well differentiate small variance in inputs?

I'm new to NN, and trying to understand some of its foundations. One question that I have is, why the derivative of an activation function is important (not the function itselt), and why it's the derivative which is tied to how the network performs learning?

For instance, when we say a constant derivative isn't good for learning, what is the intuition behind that? Is the activation function somehow like a hash function that needs to well differentiate small variance in inputs?

Source Link
Mary
  • 983
  • 6
  • 13

Activation functions in neural networks

I'm new to NN, and trying to understand the foundations. One question that I have is, why the derivative of an activation function is important, and is tied to how the network performs learning?

For instance, when we say a constant derivative isn't good for learning. What is the intuition behind that? Is the activation function somehow like a hash function that need to well differentiate small variance in inputs?