FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3016076402> ?p ?o ?g. }

• W3016076402 abstract "Although artificial neural networks (ANNs) are successful, there is still a concern among many over their black box nature. Why do they work? Could we design a transparent network? This paper presents a controllable and readable polynomial neural network (CR-PNN) for approximation, prediction, and system identification. CR-PNN is simple enough to be described as one small formula, so that we can control the approximation precision and explain the internal structure of the network. CR-PNN, in fact, essentially is the fascinating Taylor expansion in the form of network. The number of layers represents precision. Derivatives in Taylor expansion are exactly imitated by error back-propagation algorithm. Firstly, we demonstrated that CR-PNN shows excellent analysis performance to the black box system through ten synthetic data with noise. Also, the results were compared with synthetic data to substantiate its search easily towards the global optimum. Secondly, it was verified, by ten real-world applications, that CR-PNN brought better generalization capability relative to the typical ANNs that approximate depended on the nonlinear activation function. Finally, 200,000 repeated experiments, with 4898 samples, demonstrated that CR-PNN is five times more efficient than typical ANN for one epoch and ten times more efficient than typical ANN for one forward-propagation. In short, compared with the traditional neural networks, the novelties and advantages of CR-PNN include readability of the internal structure, easy to find global optimal solution, lower computational complexity, and likely better robustness to real-world approximation. (We're strong believers in Open Source, and provide CR-PNN code for others. GitHub: this https URL)" @default.
• W3016076402 created "2020-04-17" @default.
• W3016076402 creator A5037677450 @default.
• W3016076402 creator A5058637832 @default.
• W3016076402 date "2020-04-08" @default.
• W3016076402 modified "2023-09-25" @default.
• W3016076402 title "A Polynomial Neural Network with Controllable Precision and Human-Readable Topology for Prediction and System Identification." @default.
• W3016076402 cites W1481566577 @default.
• W3016076402 cites W1498436455 @default.
• W3016076402 cites W1964552793 @default.
• W3016076402 cites W1979373126 @default.
• W3016076402 cites W1980628324 @default.
• W3016076402 cites W2024060531 @default.
• W3016076402 cites W2103459159 @default.
• W3016076402 cites W2103496339 @default.
• W3016076402 cites W2156876426 @default.
• W3016076402 cites W2158143121 @default.
• W3016076402 cites W2162836072 @default.
• W3016076402 cites W2245816615 @default.
• W3016076402 cites W2319954399 @default.
• W3016076402 cites W2343337519 @default.
• W3016076402 cites W2605564896 @default.
• W3016076402 cites W2793918791 @default.
• W3016076402 cites W2808246927 @default.
• W3016076402 cites W2829536470 @default.
• W3016076402 cites W2905923365 @default.
• W3016076402 cites W3146803896 @default.
• W3016076402 hasPublicationYear "2020" @default.
• W3016076402 type Work @default.
• W3016076402 sameAs 3016076402 @default.
• W3016076402 citedByCount "1" @default.
• W3016076402 countsByYear W30160764022020 @default.
• W3016076402 crossrefType "posted-content" @default.
• W3016076402 hasAuthorship W3016076402A5037677450 @default.
• W3016076402 hasAuthorship W3016076402A5058637832 @default.
• W3016076402 hasConcept C104317684 @default.
• W3016076402 hasConcept C111919701 @default.
• W3016076402 hasConcept C11413529 @default.
• W3016076402 hasConcept C121332964 @default.
• W3016076402 hasConcept C134306372 @default.
• W3016076402 hasConcept C134342201 @default.
• W3016076402 hasConcept C154945302 @default.
• W3016076402 hasConcept C155032097 @default.
• W3016076402 hasConcept C158622935 @default.
• W3016076402 hasConcept C158946198 @default.
• W3016076402 hasConcept C175202392 @default.
• W3016076402 hasConcept C177148314 @default.
• W3016076402 hasConcept C185592680 @default.
• W3016076402 hasConcept C199845137 @default.
• W3016076402 hasConcept C33923547 @default.
• W3016076402 hasConcept C41008148 @default.
• W3016076402 hasConcept C50644808 @default.
• W3016076402 hasConcept C55493867 @default.
• W3016076402 hasConcept C62520636 @default.
• W3016076402 hasConcept C63479239 @default.
• W3016076402 hasConcept C90119067 @default.
• W3016076402 hasConcept C91873725 @default.
• W3016076402 hasConceptScore W3016076402C104317684 @default.
• W3016076402 hasConceptScore W3016076402C111919701 @default.
• W3016076402 hasConceptScore W3016076402C11413529 @default.
• W3016076402 hasConceptScore W3016076402C121332964 @default.
• W3016076402 hasConceptScore W3016076402C134306372 @default.
• W3016076402 hasConceptScore W3016076402C134342201 @default.
• W3016076402 hasConceptScore W3016076402C154945302 @default.
• W3016076402 hasConceptScore W3016076402C155032097 @default.
• W3016076402 hasConceptScore W3016076402C158622935 @default.
• W3016076402 hasConceptScore W3016076402C158946198 @default.
• W3016076402 hasConceptScore W3016076402C175202392 @default.
• W3016076402 hasConceptScore W3016076402C177148314 @default.
• W3016076402 hasConceptScore W3016076402C185592680 @default.
• W3016076402 hasConceptScore W3016076402C199845137 @default.
• W3016076402 hasConceptScore W3016076402C33923547 @default.
• W3016076402 hasConceptScore W3016076402C41008148 @default.
• W3016076402 hasConceptScore W3016076402C50644808 @default.
• W3016076402 hasConceptScore W3016076402C55493867 @default.
• W3016076402 hasConceptScore W3016076402C62520636 @default.
• W3016076402 hasConceptScore W3016076402C63479239 @default.
• W3016076402 hasConceptScore W3016076402C90119067 @default.
• W3016076402 hasConceptScore W3016076402C91873725 @default.
• W3016076402 hasLocation W30160764021 @default.
• W3016076402 hasOpenAccess W3016076402 @default.
• W3016076402 hasPrimaryLocation W30160764021 @default.
• W3016076402 hasRelatedWork W1617445017 @default.
• W3016076402 hasRelatedWork W1751450240 @default.
• W3016076402 hasRelatedWork W1861308462 @default.
• W3016076402 hasRelatedWork W2028149099 @default.
• W3016076402 hasRelatedWork W2069843418 @default.
• W3016076402 hasRelatedWork W2106224199 @default.
• W3016076402 hasRelatedWork W2110055231 @default.
• W3016076402 hasRelatedWork W2118277177 @default.
• W3016076402 hasRelatedWork W2121839474 @default.
• W3016076402 hasRelatedWork W2156237334 @default.
• W3016076402 hasRelatedWork W2355097374 @default.
• W3016076402 hasRelatedWork W2377081982 @default.
• W3016076402 hasRelatedWork W2389355558 @default.
• W3016076402 hasRelatedWork W2527007184 @default.
• W3016076402 hasRelatedWork W2771575470 @default.
• W3016076402 hasRelatedWork W3006614220 @default.
• W3016076402 hasRelatedWork W3084156817 @default.
• W3016076402 hasRelatedWork W3088841956 @default.

• next