polito.it
Politecnico di Torino (logo)

Analysis of neural network reliability in safety-critical applications

Alessandro Ianne

Analysis of neural network reliability in safety-critical applications.

Rel. Edgar Ernesto Sanchez Sanchez, Paolo Bernardi, Annachiara Ruospo. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Informatica (Computer Engineering), 2019

[img]
Preview
PDF (Tesi_di_laurea) - Tesi
Document access: Anyone
Licenza: Creative Commons Attribution Non-commercial No Derivatives.

Download (2MB) | Preview
Abstract:

Convolutional Neural Networks todays are widely used in many scenarios, thanks to their exceptional performance in terms of prediction accuracy. Despite they are considered a error-tolerant models, their deployment in safety-critical domains require a careful evaluation in order to foresee the effetcs due to system failures. Our goal is to test CNNs reliability during inference phase by highlighting when the classification results deviate from the correct one. In this work we propose a methodology that evaluates reliability through a fault-injection campaign. Permanent fault are injected at the output of multiplications between weights and input feature maps. Experimental results show that the network works properly only for faults restricted to certain locations, ensuring the same accuracy level of a fault-free inference.

Relators: Edgar Ernesto Sanchez Sanchez, Paolo Bernardi, Annachiara Ruospo
Academic year: 2018/19
Publication type: Electronic
Number of Pages: 58
Subjects:
Corso di laurea: Corso di laurea magistrale in Ingegneria Informatica (Computer Engineering)
Classe di laurea: New organization > Master science > LM-32 - COMPUTER SYSTEMS ENGINEERING
Aziende collaboratrici: UNSPECIFIED
URI: http://webthesis.biblio.polito.it/id/eprint/11548
Modify record (reserved for operators) Modify record (reserved for operators)