ISO/IEC 24029-2-2023 PDF

ISO/IEC 24029-2-2023 PDF

Artificial intelligence (AI)-Assessment of the robustness of neural networks-Part 2: Methodology for the use of formal methods

$96.50 $193.00 -50%
Product Code: ISO/IEC 24029-2
Stock In Stock
Edition: 1.
Published: 08/2023
Number of Pages: 30
File Size: 1 file, 1 Byte

Available Options

Product Description

Artificial intelligence (AI) — Assessment of the robustness of neural networks — Part 2: Methodology for the use of formal methods

Introduction: Neural networks are widely used to perform complex tasks in various contexts, such as image or natural language processing and predictive maintenance. AI system quality models comprise certain characteristics, including robustness. For example, ISO/IEC 25059:2023,[1] which extends the SQuaRE International Standards[2] to AI systems, considers in its quality model that robustness is a sub- characteristic of reliability. Demonstrating the ability of a system to maintain its level of performance under varying conditions can be done using statistical analysis, but proving it requires some form of formal analysis. In that regard formal methods can be complementary to other methods in order to increase trust in the robustness of the neural network. Formal methods are mathematical techniques for rigorous specification and verification of software and hardware systems with the goal to prove their correctness. Formal methods can be used to formally reason about neural networks and prove whether they satisfy relevant robustness properties. For example, consider a neural network classifier that takes as input an image and outputs a label from a fixed set of classes (such as car or airplane). Such a classifier can be formalized as a mathematical function that takes the pixel intensities of an image as input, computes the probabilities for each possible class from the fixed set, and returns a label corresponding to the highest probability. This formal model can then be used to mathematica

Scope: This document provides methodology for the use of formal methods to assess robustness properties of neural networks. The document focuses on how to select, apply and manage formal methods to prove robustness properties.

Be the first to write a review for this product.

Write a review

Note: HTML is not translated!
Bad           Good
ISO/IEC 24029-2-2023 PDF

ISO/IEC 24029-2-2023 PDF

$96.50 $193.00