Term	Terse explanation

Sigmoid function

An S-shaped function that maps any real number to a value between 0 and 1. Often interpreted as a probability.

Logistic function

Another name for the sigmoid function: $\sigma(x)=\frac{1}{1+e^{-x}}$σ(x)=1+e−x1​.

Activation function

A function applied to a neuron’s weighted sum to produce its output. It introduces nonlinearity (e.g., sigmoid, ReLU, tanh).

Loss function

Measures the error for one training example. Smaller loss means a better prediction.

Cost function

The aggregate (usually average or sum) of the loss over the entire training dataset. This is what training minimizes.

Softmax

Converts a vector of scores into a probability distribution whose entries sum to 1. Used for multiclass classification.

output alpha from activation function.