Scribd Logo
Upload

Welcome to Scribd!

  • W3.Why Do You Need Non-Linear Activation Functions

    Uploaded by

    JoseLuis López Molano
    8 views2 pages
    This document discusses the need for non-linear activation functions in neural networks. It provides a simple example of a neural network with one hidden layer and nonlinear activation functions that take the weighted sum of inputs as an argument and output an activated value. The nonlinear activation functions allow the network to learn nonlinear and complex decision boundaries.

    Original Description:

    Original Title

    W3.Why do you need non-linear activation functions.pptx

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Report this Document
    This document discusses the need for non-linear activation functions in neural networks. It provides a simple example of a neural network with one hidden layer and nonlinear activation functions that take the weighted sum of inputs as an argument and output an activated value. The nonlinear activation functions allow the network to learn nonlinear and complex decision boundaries.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Flag for inappropriate content
    Download as pptx, pdf, or txt
    8 views2 pages

    W3.Why Do You Need Non-Linear Activation Functions

    Uploaded by

    JoseLuis López Molano
    This document discusses the need for non-linear activation functions in neural networks. It provides a simple example of a neural network with one hidden layer and nonlinear activation functions that take the weighted sum of inputs as an argument and output an activated value. The nonlinear activation functions allow the network to learn nonlinear and complex decision boundaries.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Flag for inappropriate content
    Download as pptx, pdf, or txt
    of 2

    One hidden layer

    Neural Network

    Why do you
    deeplearning.ai need non-linear
    activation functions?
    Activation function
     
    𝑥1
     
    𝑥2 𝑦
     ^

     
    𝑥3
    Given x:
      [ 1]
    𝑧 =𝑊 [ 1 ] 𝑥+𝑏 [ 1]
     𝑎 [1 ] = 𝑔[1] ( 𝑧 [ 1] )

      [ 2]
    𝑧 =𝑊 [ 2 ] 𝑎 [1 ] +𝑏 [ 2]
     𝑎 [2 ] = 𝑔[2] ( 𝑧 [ 2] )
    Andrew Ng

    You might also like