# Perceptron

To learn what is neuro network, let’s first study a type of artificial neuron called a perceptron.

# Perceptron

Perceptrons were invented by Frank Rosenblatt in the 1950s and 1960s. A perceptron takes several binary inputs and produces a single output:

In the above example, we have three inputs, $x_1$, $x_2$ and $x_3$. The perceptron then give each input a weight, $x_1$, $x_2$ and $x_3$, and calculate the weighted sum $\sum_jw_jx_j$. The neuron’s output, 0 or 1, is determined by whether the weighted sum is less than or greater than some threshold value.

Note:

1. The weighted sum is also widely used in Fuzzy Controllers. There are plenty of researches in fuzzy neural networks.
2. The output function is also called active/transfer function can be: sgn, sigmoid neurons, ReLU.