Matches in SemOpenAlex for { <https://semopenalex.org/work/W3215605177> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3215605177 abstract "The main goal of this paper is to examine the possibility of using the 32-bit fixed-point format to represent the weights of neural networks (NN) instead of the standardly used 32-bit floating-point format in order to reduce the complexity of NN implementation. To this end, the performance of the 32-bit fixed-point format is analyzed, using an analogy between the fixed-point format and the uniform quantization that allows for the performance of the 32-bit fixed-point format to be expressed by an objective measure SQNR (Signal-to-Quantization Noise Ratio). In doing so, SQNR analysis is performed in a wide range of variance of NN weights, looking for a solution that maximizes the average SQNR in that range of variance. Also, an experiment is performed, applying the 32-bit fixed-point format to represent the weights of an MLP (Multilayer Perceptron) neural network trained for classification purposes. It is shown that the application of the 32-bit fixed-point representation of MLP weights achieves the same classification accuracy as in the case of the 32-bit floating-point representation of MLP weights, proving that the application of the 32-bit fixed-point representation of weights reduces the implementation complexity of neural networks without compromising the accuracy of classification." @default.
- W3215605177 created "2021-12-06" @default.
- W3215605177 creator A5003447533 @default.
- W3215605177 creator A5009012244 @default.
- W3215605177 creator A5021040932 @default.
- W3215605177 creator A5054385720 @default.
- W3215605177 creator A5059527265 @default.
- W3215605177 creator A5073104571 @default.
- W3215605177 date "2021-10-20" @default.
- W3215605177 modified "2023-09-27" @default.
- W3215605177 title "Analysis of 32-bit Fixed Point Quantizer in the Wide Variance Range for the Laplacian Source" @default.
- W3215605177 cites W2020644915 @default.
- W3215605177 cites W2159061947 @default.
- W3215605177 cites W2907142861 @default.
- W3215605177 cites W2955455382 @default.
- W3215605177 cites W2964046515 @default.
- W3215605177 cites W3034035469 @default.
- W3215605177 cites W3094872547 @default.
- W3215605177 cites W3096849335 @default.
- W3215605177 cites W3126542483 @default.
- W3215605177 cites W3162637948 @default.
- W3215605177 cites W3174563152 @default.
- W3215605177 doi "https://doi.org/10.1109/telsiks52058.2021.9606251" @default.
- W3215605177 hasPublicationYear "2021" @default.
- W3215605177 type Work @default.
- W3215605177 sameAs 3215605177 @default.
- W3215605177 citedByCount "2" @default.
- W3215605177 countsByYear W32156051772023 @default.
- W3215605177 crossrefType "proceedings-article" @default.
- W3215605177 hasAuthorship W3215605177A5003447533 @default.
- W3215605177 hasAuthorship W3215605177A5009012244 @default.
- W3215605177 hasAuthorship W3215605177A5021040932 @default.
- W3215605177 hasAuthorship W3215605177A5054385720 @default.
- W3215605177 hasAuthorship W3215605177A5059527265 @default.
- W3215605177 hasAuthorship W3215605177A5073104571 @default.
- W3215605177 hasConcept C11413529 @default.
- W3215605177 hasConcept C134306372 @default.
- W3215605177 hasConcept C153180895 @default.
- W3215605177 hasConcept C154945302 @default.
- W3215605177 hasConcept C159985019 @default.
- W3215605177 hasConcept C163973906 @default.
- W3215605177 hasConcept C192562407 @default.
- W3215605177 hasConcept C204323151 @default.
- W3215605177 hasConcept C28855332 @default.
- W3215605177 hasConcept C33923547 @default.
- W3215605177 hasConcept C41008148 @default.
- W3215605177 hasConcept C50644808 @default.
- W3215605177 hasConcept C61445026 @default.
- W3215605177 hasConcept C84211073 @default.
- W3215605177 hasConceptScore W3215605177C11413529 @default.
- W3215605177 hasConceptScore W3215605177C134306372 @default.
- W3215605177 hasConceptScore W3215605177C153180895 @default.
- W3215605177 hasConceptScore W3215605177C154945302 @default.
- W3215605177 hasConceptScore W3215605177C159985019 @default.
- W3215605177 hasConceptScore W3215605177C163973906 @default.
- W3215605177 hasConceptScore W3215605177C192562407 @default.
- W3215605177 hasConceptScore W3215605177C204323151 @default.
- W3215605177 hasConceptScore W3215605177C28855332 @default.
- W3215605177 hasConceptScore W3215605177C33923547 @default.
- W3215605177 hasConceptScore W3215605177C41008148 @default.
- W3215605177 hasConceptScore W3215605177C50644808 @default.
- W3215605177 hasConceptScore W3215605177C61445026 @default.
- W3215605177 hasConceptScore W3215605177C84211073 @default.
- W3215605177 hasFunder F4320329307 @default.
- W3215605177 hasLocation W32156051771 @default.
- W3215605177 hasOpenAccess W3215605177 @default.
- W3215605177 hasPrimaryLocation W32156051771 @default.
- W3215605177 hasRelatedWork W1482661175 @default.
- W3215605177 hasRelatedWork W1951967697 @default.
- W3215605177 hasRelatedWork W1983878430 @default.
- W3215605177 hasRelatedWork W2096545584 @default.
- W3215605177 hasRelatedWork W2141427150 @default.
- W3215605177 hasRelatedWork W2898065987 @default.
- W3215605177 hasRelatedWork W2952202138 @default.
- W3215605177 hasRelatedWork W3119699820 @default.
- W3215605177 hasRelatedWork W3162637948 @default.
- W3215605177 hasRelatedWork W4221148635 @default.
- W3215605177 isParatext "false" @default.
- W3215605177 isRetracted "false" @default.
- W3215605177 magId "3215605177" @default.
- W3215605177 workType "article" @default.