Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387204441> ?p ?o ?g. }
- W4387204441 endingPage "3894" @default.
- W4387204441 startingPage "3883" @default.
- W4387204441 abstract "Abstract State-of-the-art deep learning models can converse and interact with humans by understanding their emotions, but the exponential increase in model parameters has triggered an unprecedented demand for fast and low-power computing. Here, we propose a microcomb-enabled integrated optical neural network (MIONN) to perform the intelligent task of human emotion recognition at the speed of light and with low power consumption. Large-scale tensor data can be independently encoded in dozens of frequency channels generated by the on-chip microcomb and computed in parallel when flowing through the microring weight bank. To validate the proposed MIONN, we fabricated proof-of-concept chips and a prototype photonic-electronic artificial intelligence (AI) computing engine with a potential throughput up to 51.2 TOPS (tera-operations per second). We developed automatic feedback control procedures to ensure the stability and 8 bits weighting precision of the MIONN. The MIONN has successfully recognized six basic human emotions, and achieved 78.5 % accuracy on the blind test set. The proposed MIONN provides a high-speed and energy-efficient neuromorphic computing hardware for deep learning models with emotional interaction capabilities." @default.
- W4387204441 created "2023-09-30" @default.
- W4387204441 creator A5015061573 @default.
- W4387204441 creator A5018073672 @default.
- W4387204441 creator A5028868684 @default.
- W4387204441 creator A5045486077 @default.
- W4387204441 creator A5050542870 @default.
- W4387204441 creator A5053165934 @default.
- W4387204441 creator A5055207211 @default.
- W4387204441 creator A5059827848 @default.
- W4387204441 creator A5065301240 @default.
- W4387204441 creator A5068914644 @default.
- W4387204441 creator A5070001044 @default.
- W4387204441 creator A5083585383 @default.
- W4387204441 creator A5088141052 @default.
- W4387204441 date "2023-10-01" @default.
- W4387204441 modified "2023-10-13" @default.
- W4387204441 title "Human emotion recognition with a microcomb-enabled integrated optical neural network" @default.
- W4387204441 cites W1983364832 @default.
- W4387204441 cites W2110134128 @default.
- W4387204441 cites W2618530766 @default.
- W4387204441 cites W2739588406 @default.
- W4387204441 cites W2752849906 @default.
- W4387204441 cites W2798701005 @default.
- W4387204441 cites W2893774004 @default.
- W4387204441 cites W2905546103 @default.
- W4387204441 cites W2905807898 @default.
- W4387204441 cites W2919115771 @default.
- W4387204441 cites W2944119451 @default.
- W4387204441 cites W2947577774 @default.
- W4387204441 cites W2976834111 @default.
- W4387204441 cites W2977468072 @default.
- W4387204441 cites W2981207549 @default.
- W4387204441 cites W2997958396 @default.
- W4387204441 cites W3004456582 @default.
- W4387204441 cites W3014583102 @default.
- W4387204441 cites W3048797928 @default.
- W4387204441 cites W3098600872 @default.
- W4387204441 cites W3103046660 @default.
- W4387204441 cites W3110568312 @default.
- W4387204441 cites W3118265437 @default.
- W4387204441 cites W3120165331 @default.
- W4387204441 cites W3121141908 @default.
- W4387204441 cites W3127561923 @default.
- W4387204441 cites W3128451613 @default.
- W4387204441 cites W3133156045 @default.
- W4387204441 cites W3156357868 @default.
- W4387204441 cites W3159854664 @default.
- W4387204441 cites W3175324503 @default.
- W4387204441 cites W3196093339 @default.
- W4387204441 cites W3211176438 @default.
- W4387204441 cites W3216922697 @default.
- W4387204441 cites W4210275959 @default.
- W4387204441 cites W4210305137 @default.
- W4387204441 cites W4210884760 @default.
- W4387204441 cites W4221158782 @default.
- W4387204441 cites W4224026682 @default.
- W4387204441 cites W4224992102 @default.
- W4387204441 cites W4225485808 @default.
- W4387204441 cites W4285251817 @default.
- W4387204441 cites W4293141353 @default.
- W4387204441 cites W4293812122 @default.
- W4387204441 cites W4304957538 @default.
- W4387204441 cites W4312177931 @default.
- W4387204441 cites W4313197653 @default.
- W4387204441 cites W4313466174 @default.
- W4387204441 cites W4313576662 @default.
- W4387204441 cites W4313596643 @default.
- W4387204441 cites W4313837456 @default.
- W4387204441 cites W4313894114 @default.
- W4387204441 cites W4318219754 @default.
- W4387204441 doi "https://doi.org/10.1515/nanoph-2023-0298" @default.
- W4387204441 hasPublicationYear "2023" @default.
- W4387204441 type Work @default.
- W4387204441 citedByCount "0" @default.
- W4387204441 crossrefType "journal-article" @default.
- W4387204441 hasAuthorship W4387204441A5015061573 @default.
- W4387204441 hasAuthorship W4387204441A5018073672 @default.
- W4387204441 hasAuthorship W4387204441A5028868684 @default.
- W4387204441 hasAuthorship W4387204441A5045486077 @default.
- W4387204441 hasAuthorship W4387204441A5050542870 @default.
- W4387204441 hasAuthorship W4387204441A5053165934 @default.
- W4387204441 hasAuthorship W4387204441A5055207211 @default.
- W4387204441 hasAuthorship W4387204441A5059827848 @default.
- W4387204441 hasAuthorship W4387204441A5065301240 @default.
- W4387204441 hasAuthorship W4387204441A5068914644 @default.
- W4387204441 hasAuthorship W4387204441A5070001044 @default.
- W4387204441 hasAuthorship W4387204441A5083585383 @default.
- W4387204441 hasAuthorship W4387204441A5088141052 @default.
- W4387204441 hasBestOaLocation W43872044411 @default.
- W4387204441 hasConcept C108583219 @default.
- W4387204441 hasConcept C113775141 @default.
- W4387204441 hasConcept C118524514 @default.
- W4387204441 hasConcept C120665830 @default.
- W4387204441 hasConcept C121332964 @default.
- W4387204441 hasConcept C127413603 @default.
- W4387204441 hasConcept C148204187 @default.
- W4387204441 hasConcept C151927369 @default.