# Sum of Squares Function

(Redirected from Sum-of-Squares Operation)

Jump to navigation
Jump to search
A Sum of Squares Function is a metric based on the sum operation on square functions.

**Context:**- It can be represented as [math]\displaystyle{ \sum^N_1 (x^2_i) }[/math].

**Example(s):**- [math]\displaystyle{ \sum_{i=1}^{n}\left(y_{i}-\bar{y}\right)^2 }[/math] where [math]\displaystyle{ \bar{y} }[/math] is the mean (sum of square residuals).
- …

**Counter-Example(s):****See:**Regression Tree Splitting Criterion, Least Squares, Nonlinear Least Squares, Partition of Sums of Qquares.

## References

### 2017

- (Wikipedia, 2017) ⇒ https://en.wikipedia.org/wiki/sum_of_squares Retrieved:2017-10-2.
- In mathematics, statistics and elsewhere,
**sums of squares**occur in a number of contexts:- For the "sum of squared deviations", see Least squares.
- For the "sum of squared differences", see Mean squared error.
- For the "sum of squared error", see Residual sum of squares.
- For the "sum of squares due to lack of fit", see Lack-of-fit sum of squares.
- For sums of squares relating to model predictions, see Explained sum of squares.
- For sums of squares relating to observations, see Total sum of squares.
- For sums of squared deviations, see Squared deviations.
- For modelling involving sums of squares, see Analysis of variance.
- For modelling involving the multivariate generalisation of sums of squares, see Multivariate analysis of variance

- In mathematics, statistics and elsewhere,

### 2014

- http://en.wikipedia.org/wiki/Least_squares#Problem_statement
- The least squares method finds its optimum when the sum,
*S*, of squared residuals :[math]\displaystyle{ S=\sum_{i=1}^{n}{r_i}^2 }[/math]

- The least squares method finds its optimum when the sum,

### 1994

- (Hagan & Menhaj, 1994) ⇒ Martin T. Hagan, and Mohammad B. Menhaj. (1994). “Training Feedforward Networks with the Marquardt Algorithm.” In: IEEE Transactions on Neural Networks Journal, 5(6). doi:10.1109/72.329697
- QUOTE: ....If we assume that [math]\displaystyle{ V(\underline{x}) }[/math] is a sum of squares function [math]\displaystyle{ V(\underline{x}) = \sum^N_{i=q} e^2_i(\underline{x}) }[/math] ...