Sigmoid Function
/ˈsɪɡmɔɪd/
Sigmoid Function: An activation function that maps inputs to values between 0 and 1: f(x) = 1/(1 + e^(-x)). Sigmoid is used for binary classification output layers and was historically popular for hidden layers. However, it suffers from vanishing gradient problems in deep networks.
In italiano: Funzione SigmoideLegge II · Probabilità, softmax e modelli generativiSigmoid is used for binary classification output layers and was historically popular for hidden layers. However, it suffers from vanishing gradient problems in deep networks.
Examples
- Binary classification output
- Logistic regression
- Gate mechanisms in LSTM
Attivazioni e derivate
Confronta le curve: attiva ogni funzione e la sua derivata per osservare saturazione e gradiente.
Autovalutazione
Tre domande per verificare la comprensione della voce. Le spiegazioni restano disponibili anche senza JavaScript.