Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092885274> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3092885274 abstract "Over the past few years, deep neural networks have shown excellent results in multiple tasks, however, there is still an increasing need to address the problem of interpretability to improve model transparency, performance, and safety. Achieving eXplainable Artificial Intelligence (XAI) by combining neural networks with continuous logic and multi-criteria decision-making tools is one of the most promising ways to approach this problem: by this combination, the black-box nature of neural models can be reduced. The continuous logic-based neural model uses so-called Squashing activation functions, a parametric family of functions that satisfy natural invariance requirements and contain rectified linear units as a particular case. This work demonstrates the first benchmark tests that measure the performance of Squashing functions in neural networks. Three experiments were carried out to examine their usability and a comparison with the most popular activation functions was made for five different network types. The performance was determined by measuring the accuracy, loss, and time per epoch. These experiments and the conducted benchmarks have proven that the use of Squashing functions is possible and similar in performance to conventional activation functions. Moreover, a further experiment was conducted by implementing nilpotent logical gates to demonstrate how simple classification tasks can be solved successfully and with high performance. The results indicate that due to the embedded nilpotent logical operators and the differentiability of the Squashing function, it is possible to solve classification problems, where other commonly used activation functions fail." @default.
- W3092885274 created "2020-10-22" @default.
- W3092885274 creator A5054572006 @default.
- W3092885274 creator A5056459728 @default.
- W3092885274 creator A5059510061 @default.
- W3092885274 creator A5068838710 @default.
- W3092885274 date "2020-10-17" @default.
- W3092885274 modified "2023-10-05" @default.
- W3092885274 title "Squashing activation functions in benchmark tests: towards eXplainable Artificial Intelligence using continuous-valued logic" @default.
- W3092885274 cites W1170012209 @default.
- W3092885274 cites W1995380043 @default.
- W3092885274 cites W2040523117 @default.
- W3092885274 cites W2057066113 @default.
- W3092885274 cites W2075090033 @default.
- W3092885274 cites W2087013902 @default.
- W3092885274 cites W2111072639 @default.
- W3092885274 cites W2112796928 @default.
- W3092885274 cites W2147800946 @default.
- W3092885274 cites W2496338429 @default.
- W3092885274 cites W2555454552 @default.
- W3092885274 cites W2781044394 @default.
- W3092885274 cites W2894268779 @default.
- W3092885274 cites W2912565176 @default.
- W3092885274 cites W3035256913 @default.
- W3092885274 cites W564030374 @default.
- W3092885274 hasPublicationYear "2020" @default.
- W3092885274 type Work @default.
- W3092885274 sameAs 3092885274 @default.
- W3092885274 citedByCount "0" @default.
- W3092885274 crossrefType "posted-content" @default.
- W3092885274 hasAuthorship W3092885274A5054572006 @default.
- W3092885274 hasAuthorship W3092885274A5056459728 @default.
- W3092885274 hasAuthorship W3092885274A5059510061 @default.
- W3092885274 hasAuthorship W3092885274A5068838710 @default.
- W3092885274 hasConcept C119857082 @default.
- W3092885274 hasConcept C13280743 @default.
- W3092885274 hasConcept C134306372 @default.
- W3092885274 hasConcept C154945302 @default.
- W3092885274 hasConcept C185798385 @default.
- W3092885274 hasConcept C202615002 @default.
- W3092885274 hasConcept C205649164 @default.
- W3092885274 hasConcept C2781067378 @default.
- W3092885274 hasConcept C33923547 @default.
- W3092885274 hasConcept C38365724 @default.
- W3092885274 hasConcept C41008148 @default.
- W3092885274 hasConcept C50644808 @default.
- W3092885274 hasConceptScore W3092885274C119857082 @default.
- W3092885274 hasConceptScore W3092885274C13280743 @default.
- W3092885274 hasConceptScore W3092885274C134306372 @default.
- W3092885274 hasConceptScore W3092885274C154945302 @default.
- W3092885274 hasConceptScore W3092885274C185798385 @default.
- W3092885274 hasConceptScore W3092885274C202615002 @default.
- W3092885274 hasConceptScore W3092885274C205649164 @default.
- W3092885274 hasConceptScore W3092885274C2781067378 @default.
- W3092885274 hasConceptScore W3092885274C33923547 @default.
- W3092885274 hasConceptScore W3092885274C38365724 @default.
- W3092885274 hasConceptScore W3092885274C41008148 @default.
- W3092885274 hasConceptScore W3092885274C50644808 @default.
- W3092885274 hasLocation W30928852741 @default.
- W3092885274 hasOpenAccess W3092885274 @default.
- W3092885274 hasPrimaryLocation W30928852741 @default.
- W3092885274 hasRelatedWork W127974184 @default.
- W3092885274 hasRelatedWork W1984178894 @default.
- W3092885274 hasRelatedWork W2065306152 @default.
- W3092885274 hasRelatedWork W2096011958 @default.
- W3092885274 hasRelatedWork W2107725879 @default.
- W3092885274 hasRelatedWork W2211174136 @default.
- W3092885274 hasRelatedWork W2245599531 @default.
- W3092885274 hasRelatedWork W2271846546 @default.
- W3092885274 hasRelatedWork W2282514586 @default.
- W3092885274 hasRelatedWork W2323614877 @default.
- W3092885274 hasRelatedWork W2475282529 @default.
- W3092885274 hasRelatedWork W2795944650 @default.
- W3092885274 hasRelatedWork W2902429474 @default.
- W3092885274 hasRelatedWork W2986628990 @default.
- W3092885274 hasRelatedWork W3004164323 @default.
- W3092885274 hasRelatedWork W3005889292 @default.
- W3092885274 hasRelatedWork W3014521881 @default.
- W3092885274 hasRelatedWork W3172526549 @default.
- W3092885274 hasRelatedWork W3174804935 @default.
- W3092885274 hasRelatedWork W755477143 @default.
- W3092885274 isParatext "false" @default.
- W3092885274 isRetracted "false" @default.
- W3092885274 magId "3092885274" @default.
- W3092885274 workType "article" @default.