Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384268549> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4384268549 abstract "Neural networks have shown great success in many machine learning related tasks, due to their ability to act as general function approximators. Recent work has demonstrated the effectiveness of neural networks in control systems (known as neural feedback loops), most notably by using a neural network as a controller. However, one of the big challenges of this approach is that neural networks have been shown to be sensitive to adversarial attacks. This means that, unless they are designed properly, they are not an ideal candidate for controllers due to issues with robustness and uncertainty, which are pivotal aspects of control systems. There has been initial work on robustness to both analyse and design dynamical systems with neural network controllers. However, one prominent issue with these methods is that they use existing neural network architectures tailored for traditional machine learning tasks. These structures may not be appropriate for neural network controllers and it is important to consider alternative architectures. This paper considers rational neural networks and presents novel rational activation functions, which can be used effectively in robustness problems for neural feedback loops. Rational activation functions are replaced by a general rational neural network structure, which is convex in the neural network's parameters. A method is proposed to recover a stabilising controller from a Sum of Squares feasibility test. This approach is then applied to a refined rational neural network which is more compatible with Sum of Squares programming. Numerical examples show that this method can successfully recover stabilising rational neural network controllers for neural feedback loops with non-linear plants with noise and parametric uncertainty." @default.
- W4384268549 created "2023-07-14" @default.
- W4384268549 creator A5008526337 @default.
- W4384268549 creator A5053811056 @default.
- W4384268549 date "2023-07-12" @default.
- W4384268549 modified "2023-10-17" @default.
- W4384268549 title "Rational Neural Network Controllers" @default.
- W4384268549 doi "https://doi.org/10.48550/arxiv.2307.06287" @default.
- W4384268549 hasPublicationYear "2023" @default.
- W4384268549 type Work @default.
- W4384268549 citedByCount "0" @default.
- W4384268549 crossrefType "posted-content" @default.
- W4384268549 hasAuthorship W4384268549A5008526337 @default.
- W4384268549 hasAuthorship W4384268549A5053811056 @default.
- W4384268549 hasBestOaLocation W43842685491 @default.
- W4384268549 hasConcept C104317684 @default.
- W4384268549 hasConcept C154945302 @default.
- W4384268549 hasConcept C175202392 @default.
- W4384268549 hasConcept C177973122 @default.
- W4384268549 hasConcept C185592680 @default.
- W4384268549 hasConcept C2775924081 @default.
- W4384268549 hasConcept C41008148 @default.
- W4384268549 hasConcept C47446073 @default.
- W4384268549 hasConcept C50644808 @default.
- W4384268549 hasConcept C55493867 @default.
- W4384268549 hasConcept C63479239 @default.
- W4384268549 hasConcept C86582703 @default.
- W4384268549 hasConceptScore W4384268549C104317684 @default.
- W4384268549 hasConceptScore W4384268549C154945302 @default.
- W4384268549 hasConceptScore W4384268549C175202392 @default.
- W4384268549 hasConceptScore W4384268549C177973122 @default.
- W4384268549 hasConceptScore W4384268549C185592680 @default.
- W4384268549 hasConceptScore W4384268549C2775924081 @default.
- W4384268549 hasConceptScore W4384268549C41008148 @default.
- W4384268549 hasConceptScore W4384268549C47446073 @default.
- W4384268549 hasConceptScore W4384268549C50644808 @default.
- W4384268549 hasConceptScore W4384268549C55493867 @default.
- W4384268549 hasConceptScore W4384268549C63479239 @default.
- W4384268549 hasConceptScore W4384268549C86582703 @default.
- W4384268549 hasLocation W43842685491 @default.
- W4384268549 hasOpenAccess W4384268549 @default.
- W4384268549 hasPrimaryLocation W43842685491 @default.
- W4384268549 hasRelatedWork W1548385991 @default.
- W4384268549 hasRelatedWork W1584270863 @default.
- W4384268549 hasRelatedWork W1595652908 @default.
- W4384268549 hasRelatedWork W180587397 @default.
- W4384268549 hasRelatedWork W2063512127 @default.
- W4384268549 hasRelatedWork W2085961337 @default.
- W4384268549 hasRelatedWork W2106547445 @default.
- W4384268549 hasRelatedWork W2378845890 @default.
- W4384268549 hasRelatedWork W2533573066 @default.
- W4384268549 hasRelatedWork W651238688 @default.
- W4384268549 isParatext "false" @default.
- W4384268549 isRetracted "false" @default.
- W4384268549 workType "article" @default.