Syntactic vs Semantic Linear Abstraction and Refinement of Neural Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F23%3A00133938" target="_blank" >RIV/00216224:14330/23:00133938 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-031-45329-8_19" target="_blank" >http://dx.doi.org/10.1007/978-3-031-45329-8_19</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-45329-8_19" target="_blank" >10.1007/978-3-031-45329-8_19</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Syntactic vs Semantic Linear Abstraction and Refinement of Neural Networks

Popis výsledku v původním jazyce

Abstraction is a key verification technique to improve scalability. However, its use for neural networks is so far extremely limited. Previous approaches for abstracting classification networks replace several neurons with one of them that is similar enough. We can classify the similarity as defined either syntactically (using quantities on the connections between neurons) or semantically (on the activation values of neurons for various inputs). Unfortunately, the previous approaches only achieve moderate reductions, when implemented at all. In this work, we provide a more flexible framework, where a neuron can be replaced with a linear combination of other neurons, improving the reduction. We apply this approach both on syntactic and semantic abstractions, and implement and evaluate them experimentally. Further, we introduce a refinement method for our abstractions, allowing for finding a better balance between reduction and precision.

Název v anglickém jazyce

Syntactic vs Semantic Linear Abstraction and Refinement of Neural Networks

Popis výsledku anglicky

Abstraction is a key verification technique to improve scalability. However, its use for neural networks is so far extremely limited. Previous approaches for abstracting classification networks replace several neurons with one of them that is similar enough. We can classify the similarity as defined either syntactically (using quantities on the connections between neurons) or semantically (on the activation values of neurons for various inputs). Unfortunately, the previous approaches only achieve moderate reductions, when implemented at all. In this work, we provide a more flexible framework, where a neuron can be replaced with a linear combination of other neurons, improving the reduction. We apply this approach both on syntactic and semantic abstractions, and implement and evaluate them experimentally. Further, we introduce a refinement method for our abstractions, allowing for finding a better balance between reduction and precision.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Automated Technology for Verification and Analysis. ATVA 2023

ISBN

9783031453281

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

21

Strana od-do

401-421

Název nakladatele

Springer

Místo vydání

Singapore

Místo konání akce

Singapore

Datum konání akce

1. 1. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—