An initial model for a function approximator is the perceptron. It has a set of learnable weights \( w_0, w_1, ... , w_K \) and outputs either \( 0 \) or \( 1 \) depending on its given \(K\)-dimensional input \( \htmlClass{sdt-0000000103}{u} = (\htmlClass{sdt-0000000103}{u}_1, \htmlClass{sdt-0000000103}{u} _2, ..., \htmlClass{sdt-0000000103}{u} _K) \). The perceptron can learn functions for solving a very simplistic classification problem.
| \( f \) | This is the symbol for a function. It is commonly used in algebra, and (multivariate) calculus. |
| \( i \) | This is the symbol for an iterator, a variable that changes value to refer to a sequence of elements. |
| \( u \) | This symbol denotes the input of a model. |