From Theory to Practice: Incorporating ML Models into Safety-Critical Systems
15. prosince 2023
Řečníci
Lucas García
Speaker · 0 followers
O prezentaci
Neural networks can obtain state-of-the-art performance in various tasks, including image classification, object detection, speech recognition, and machine translation. Due to this impressive performance, there has been a desire to utilize neural networks for applications in industries with safety-critical components, such as aerospace, automotive, and healthcare. However, while these industries have established processes for verifying and validating traditional software, it is often unclear how to verify the reliability of neural networks. This issue is especially prevalent in aviation, where there is potential to revolutionize the industry. However, existing airborne certification standards present major incompatibilities with Machine Learning technology. These include issues with ML model traceability and explainability and the inadequacy of traditional coverage metrics. The certification of ML-based airborne systems is problematic due to these incompatibilities. Furthermore, new certification standards intended to address these challenges are not yet released. In this talk, we’ll introduce a case study for certifying an airborne machine learning system. We’ll build a runway sign classification system that receives images from a forward-facing camera in the aircraft and then detects airport runway signs, aiding the pilot in navigation and situational awareness at the airport. We propose and implement a custom ML certification workflow for machine learning systems based on existing certification standards to tackle the previously mentioned challenges. We will walk you through all the steps in the workflow, from defining the ML requirements, managing the data, training the model, and verifying its performance to the implementation of the system in hardware and validation of the requirements. This case study will provide insights and potential solutions across industries with safety-critical components seeking to integrate neural networks into their operations.Neural networks can obtain state-of-the-art performance in various tasks, including image classification, object detection, speech recognition, and machine translation. Due to this impressive performance, there has been a desire to utilize neural networks for applications in industries with safety-critical components, such as aerospace, automotive, and healthcare. However, while these industries have established processes for verifying and validating traditional software, it is often unclear how…
Organizátor
NeurIPS 2023
Account · 645 followers
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Variational Monte Carlo on a Budget — Fine-tuning pre-trained Neural Wavefunctions
Watch later
Leon Gerard, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability
Watch later
Haotian Xue, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Effective Robustness against Natural Distribution Shifts for Models with Different Training Data
Watch later
Zhouxing Shi, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Panel Discussion
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Contributed Talk
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Tailoring Self-Attention for Graph via Rooted Subtrees
Watch later
Siyuan Huang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%