# estimateNetworkOutputBounds

## Syntax

## Description

`[`

estimates the lower and upper output bounds, `YLower`

,`YUpper`

] = estimateNetworkOutputBounds(`net`

,`XLower`

,`XUpper`

)`YLower`

and
`YUpper`

, respectively, of the network `net`

for input
within the bounds specified by `XLower`

and `XUpper`

.

The function estimates the range of output values that the network returns when the input is between the specified lower and upper bounds. Use this function to estimate how sensitive the network predictions are to input perturbation.

The `estimateNetworkOutputBounds`

function requires the Deep Learning Toolbox Verification Library support package. If this support package is not installed, use the
**Add-On Explorer**. To open the **Add-On Explorer**, go
to the MATLAB^{®} Toolstrip and click **Add-Ons** > **Get Add-Ons**.

verifies the adversarial robustness with additional options specified by one or more
name-value arguments.`result`

= estimateNetworkOutputBounds(___,`Name=Value`

)

## Examples

## Input Arguments

## Output Arguments

## Algorithms

Let *X* be the input for which you want to estimate the output bounds. To
use the `estimateNetworkOutputBounds`

function, you must specify a lower
and upper bound for the input. For example, let $$\u03f5$$ be a small perturbation. You can define a lower and upper bound for the input
as $${X}_{\text{lower}}=X-\u03f5$$ and $${X}_{\text{upper}}=X+\u03f5$$, respectively.

To estimate the output bounds for the network `net`

and the input bounds
*X*_{lower} and
*X*_{upper}, the function performs these steps.

Create an input set using the lower and upper input bounds.

Pass the input set through the network and return an output set. To reduce computational overhead, the function performs abstract interpretation by approximating the output of each layer using the DeepPoly [2] method.

Return the minimum and maximum estimated output values for the input set.

If you specify multiple pairs of input lower and upper bounds, then the function estimates the output bounds for each pair of input bounds.

**Note**

Because of floating-point round-off error, the output bounds might be slightly different when working with networks produced using C/C++ code generation.

## References

[1] Goodfellow, Ian J., Jonathon Shlens, and Christian Szegedy. “Explaining and Harnessing Adversarial Examples.” Preprint, submitted March 20, 2015. https://arxiv.org/abs/1412.6572.

[2] Singh, Gagandeep, Timon Gehr,
Markus Püschel, and Martin Vechev. “An Abstract Domain for Certifying Neural Networks”.
*Proceedings of the ACM on Programming Languages* 3, no. POPL (January 2,
2019): 1–30. https://doi.org/10.1145/3290354.

## Extended Capabilities

## Version History

**Introduced in R2022b**