FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3147483309> ?p ?o ?g. }

• W3147483309 abstract "We describe a quantum-assisted machine learning (QAML) method in which multivariate data is encoded into quantum states in a Hilbert space whose dimension is exponentially large in the length of the data vector. Learning in this space occurs through applying a low-depth quantum circuit with a tree tensor network (TTN) topology, which acts as an unsupervised feature extractor to identify the most relevant quantum states in a data-driven fashion. This unsupervised feature extractor then feeds a supervised linear classifier and encodes the output in a small-dimensional quantum register. In contrast to previous work on emph{quantum-inspired} TTN classifiers, in which the embedding map and class decision weights did not map the data to well-defined quantum states, we present an approach that can be implemented on gate-based quantum computing devices. In particular, we identify an embedding map with accuracy similar to exponential machines (Novikov emph{et al.}, arXiv:1605.03795), but which produces valid quantum states from classical data vectors, and utilize manifold-based gradient optimization schemes to produce isometric operations mapping quantum states to a register of qubits defining a class decision. We detail methods for efficiently obtaining one- and two-point correlation functions of the decision boundary vectors of the quantum model, which can be used for model interpretability, as well as methods for obtaining classifications from partial data vectors. Further, we show that the use of isometric tensors can significantly aid in the human interpretability of the correlation functions extracted from the decision weights, and may produce models that are less susceptible to adversarial perturbations. We demonstrate our methodologies in applications utilizing the MNIST handwritten digit dataset and a multivariate timeseries dataset of human activity recognition." @default.
• W3147483309 created "2021-04-13" @default.
• W3147483309 creator A5049902273 @default.
• W3147483309 creator A5087345291 @default.
• W3147483309 date "2021-10-07" @default.
• W3147483309 modified "2023-10-13" @default.
• W3147483309 title "Tree-tensor-network classifiers for machine learning: From quantum inspired to quantum assisted" @default.
• W3147483309 cites W1553535237 @default.
• W3147483309 cites W1973653436 @default.
• W3147483309 cites W1983886273 @default.
• W3147483309 cites W1993482030 @default.
• W3147483309 cites W2014461107 @default.
• W3147483309 cites W2036463035 @default.
• W3147483309 cites W2037768897 @default.
• W3147483309 cites W2041132213 @default.
• W3147483309 cites W2045512849 @default.
• W3147483309 cites W2052891002 @default.
• W3147483309 cites W2082946462 @default.
• W3147483309 cites W2086731084 @default.
• W3147483309 cites W2093774709 @default.
• W3147483309 cites W2137147061 @default.
• W3147483309 cites W2339327743 @default.
• W3147483309 cites W2559394418 @default.
• W3147483309 cites W2566002283 @default.
• W3147483309 cites W2617994470 @default.
• W3147483309 cites W2736592352 @default.
• W3147483309 cites W2752623698 @default.
• W3147483309 cites W2753545915 @default.
• W3147483309 cites W2755418751 @default.
• W3147483309 cites W2781738013 @default.
• W3147483309 cites W2794444783 @default.
• W3147483309 cites W2794727009 @default.
• W3147483309 cites W2796293949 @default.
• W3147483309 cites W2898121159 @default.
• W3147483309 cites W2903221501 @default.
• W3147483309 cites W2910259907 @default.
• W3147483309 cites W2926552232 @default.
• W3147483309 cites W2942828225 @default.
• W3147483309 cites W2943955321 @default.
• W3147483309 cites W2955078219 @default.
• W3147483309 cites W2971476734 @default.
• W3147483309 cites W2978683479 @default.
• W3147483309 cites W3009313620 @default.
• W3147483309 cites W3015983231 @default.
• W3147483309 cites W3016208849 @default.
• W3147483309 cites W3038583210 @default.
• W3147483309 cites W3046071764 @default.
• W3147483309 cites W3075559820 @default.
• W3147483309 cites W3091811465 @default.
• W3147483309 cites W3094595762 @default.
• W3147483309 cites W3098662938 @default.
• W3147483309 cites W3099497510 @default.
• W3147483309 cites W3099956647 @default.
• W3147483309 cites W3100068159 @default.
• W3147483309 cites W3100993774 @default.
• W3147483309 cites W3101479050 @default.
• W3147483309 cites W3102320711 @default.
• W3147483309 cites W3103438630 @default.
• W3147483309 cites W3103713775 @default.
• W3147483309 cites W3103945605 @default.
• W3147483309 cites W3104022488 @default.
• W3147483309 cites W3104428150 @default.
• W3147483309 cites W3111394828 @default.
• W3147483309 cites W3111799909 @default.
• W3147483309 cites W3136233239 @default.
• W3147483309 cites W3137771865 @default.
• W3147483309 cites W3154892646 @default.
• W3147483309 cites W3161721222 @default.
• W3147483309 cites W3166543104 @default.
• W3147483309 cites W3178653085 @default.
• W3147483309 cites W2067581829 @default.
• W3147483309 doi "https://doi.org/10.1103/physreva.104.042408" @default.
• W3147483309 hasPublicationYear "2021" @default.
• W3147483309 type Work @default.
• W3147483309 sameAs 3147483309 @default.
• W3147483309 citedByCount "10" @default.
• W3147483309 countsByYear W31474833092022 @default.
• W3147483309 countsByYear W31474833092023 @default.
• W3147483309 crossrefType "journal-article" @default.
• W3147483309 hasAuthorship W3147483309A5049902273 @default.
• W3147483309 hasAuthorship W3147483309A5087345291 @default.
• W3147483309 hasBestOaLocation W31474833092 @default.
• W3147483309 hasConcept C11413529 @default.
• W3147483309 hasConcept C121332964 @default.
• W3147483309 hasConcept C12267149 @default.
• W3147483309 hasConcept C137019171 @default.
• W3147483309 hasConcept C154945302 @default.
• W3147483309 hasConcept C15706264 @default.
• W3147483309 hasConcept C2779094486 @default.
• W3147483309 hasConcept C33923547 @default.
• W3147483309 hasConcept C41008148 @default.
• W3147483309 hasConcept C51003876 @default.
• W3147483309 hasConcept C62520636 @default.
• W3147483309 hasConcept C84114770 @default.
• W3147483309 hasConceptScore W3147483309C11413529 @default.
• W3147483309 hasConceptScore W3147483309C121332964 @default.
• W3147483309 hasConceptScore W3147483309C12267149 @default.
• W3147483309 hasConceptScore W3147483309C137019171 @default.
• W3147483309 hasConceptScore W3147483309C154945302 @default.
• W3147483309 hasConceptScore W3147483309C15706264 @default.

• next