Hyperbolic Tangent Neuron

From GM-RKB
(Redirected from hyperbolic tangent neuron)
Jump to navigation Jump to search

A Hyperbolic Tangent Neuron is an artificial neuron that uses a Hyperbolic Tangent Activation Function.



References

2017

  • (Mate Labs, 2017) ⇒ Mate Labs Aug 23, 2017. Secret Sauce behind the beauty of Deep Learning: Beginners guide to Activation Functions
    • QUOTE: Hyperbolic tangent (TanH)  —  It looks like a scaled sigmoid function. Data is centered around zero, so the derivatives will be higher. Tanh quickly converges than sigmoid and logistic activation functions.

      [math]\displaystyle{ f(x)=\tanh(x)=\dfrac{2}{1+e^{-2x}} -2 }[/math]

      Range: [math]\displaystyle{ (-1, 1) }[/math]

      Examples: [math]\displaystyle{ \tanh(2) = 0.9640,\; \tanh(-0.567) = -0.5131, \; \tanh(0) = 0 }[/math]


.