Formal and Practical Elements for the Certification of Machine Learning Systems

• URL: http://arxiv.org/abs/2310.03217v1
• Date: Thu, 5 Oct 2023 00:20:59 GMT
• Title: Formal and Practical Elements for the Certification of Machine Learning Systems
• Authors: Jean-Guillaume Durand, Arthur Dubois, Robert J. Moss
• Abstract summary: We show how parameters of machine learning models are not hand-coded nor derived from physics but learned from data. As a result, requirements cannot be directly traced to lines of code, hindering the current bottom-up aerospace certification paradigm. Based on a scalable statistical verifier, our proposed framework is model-agnostic and tool-independent.
• Score: 0.9217021281095907
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Over the past decade, machine learning has demonstrated impressive results, often surpassing human capabilities in sensing tasks relevant to autonomous flight. Unlike traditional aerospace software, the parameters of machine learning models are not hand-coded nor derived from physics but learned from data. They are automatically adjusted during a training phase, and their values do not usually correspond to physical requirements. As a result, requirements cannot be directly traced to lines of code, hindering the current bottom-up aerospace certification paradigm. This paper attempts to address this gap by 1) demystifying the inner workings and processes to build machine learning models, 2) formally establishing theoretical guarantees given by those processes, and 3) complementing these formal elements with practical considerations to develop a complete certification argument for safety-critical machine learning systems. Based on a scalable statistical verifier, our proposed framework is model-agnostic and tool-independent, making it adaptable to many use cases in the industry. We demonstrate results on a widespread application in autonomous flight: vision-based landing.

Related papers

• AI Enhanced Control Engineering Methods [66.08455276899578]
  We explore how AI tools can be useful in control applications. Two immediate applications are linearization of system dynamics for local stability analysis or for state estimation using Kalman filters. In addition, we explore the use of machine learning models for global parameterizations of state vectors and control inputs in model predictive control applications.
  arXiv  Detail & Related papers  (2023-06-08T20:31:14Z)
• Machine Learning with Requirements: a Manifesto [114.97965827971132]
  We argue that requirements definition and satisfaction can go a long way to make machine learning models even more fitting to the real world. We show how the requirements specification can be fruitfully integrated into the standard machine learning development pipeline.
  arXiv  Detail & Related papers  (2023-04-07T14:47:13Z)
• Framework for Certification of AI-Based Systems [0.0]
  The current certification process for aerospace software is not adapted to "AI-based" algorithms such as deep neural networks. This paper proposes a framework and principles that could be used to establish certification methods for neural network models.
  arXiv  Detail & Related papers  (2023-02-21T23:08:37Z)
• DetAIL : A Tool to Automatically Detect and Analyze Drift In Language [8.968228078113189]
  This work aims to ensure that machine learning and deep learning-based systems are as trusted as traditional software. Current systems rely on scheduled re-training of these models as new data kicks in. We propose to measure the data drift that takes place when new data kicks in so that one can adaptively re-train the models whenever re-training is actually required.
  arXiv  Detail & Related papers  (2022-11-03T19:50:12Z)
• Incremental Online Learning Algorithms Comparison for Gesture and Visual Smart Sensors [68.8204255655161]
  This paper compares four state-of-the-art algorithms in two real applications: gesture recognition based on accelerometer data and image classification. Our results confirm these systems' reliability and the feasibility of deploying them in tiny-memory MCUs.
  arXiv  Detail & Related papers  (2022-09-01T17:05:20Z)
• SOLIS -- The MLOps journey from data acquisition to actionable insights [62.997667081978825]
  In this paper we present a unified deployment pipeline and freedom-to-operate approach that supports all requirements while using basic cross-platform tensor framework and script language engines. This approach however does not supply the needed procedures and pipelines for the actual deployment of machine learning capabilities in real production grade systems.
  arXiv  Detail & Related papers  (2021-12-22T14:45:37Z)
• Multi Agent System for Machine Learning Under Uncertainty in Cyber Physical Manufacturing System [78.60415450507706]
  Recent advancements in predictive machine learning has led to its application in various use cases in manufacturing. Most research focused on maximising predictive accuracy without addressing the uncertainty associated with it. In this paper, we determine the sources of uncertainty in machine learning and establish the success criteria of a machine learning system to function well under uncertainty.
  arXiv  Detail & Related papers  (2021-07-28T10:28:05Z)
• A Review of Formal Methods applied to Machine Learning [0.6853165736531939]
  We review state-of-the-art formal methods applied to the emerging field of the verification of machine learning systems. We first recall established formal methods and their current use in an exemplar safety-critical field, avionic software. We then provide a comprehensive and detailed review of the formal methods developed so far for machine learning, highlighting their strengths and limitations.
  arXiv  Detail & Related papers  (2021-04-06T12:48:17Z)
• Towards CRISP-ML(Q): A Machine Learning Process Model with Quality Assurance Methodology [53.063411515511056]
  We propose a process model for the development of machine learning applications. The first phase combines business and data understanding as data availability oftentimes affects the feasibility of the project. The sixth phase covers state-of-the-art approaches for monitoring and maintenance of a machine learning applications.
  arXiv  Detail & Related papers  (2020-03-11T08:25:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.