Matches in SemOpenAlex for { <https://semopenalex.org/work/W2771920568> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W2771920568 abstract "We use a quantum annealing D-Wave 2X (1,152-qubit) computer to generate sparse representations of Canny-filtered, center-cropped 30x30 CIFAR-10 images. Each binary neuron (qubit) represents a feature kernel obtained initially by imprinting on a randomly chosen 5x5 image patch and then adapted via an off-line Hebbian learning protocol using the sparse solutions generated by the D-Wave. When using binary neurons, the energy function is non-convex (multiple local-minima) and finding a global minimum is NP-hard. Quantum annealing provides a strategy for finding sparse representations that correspond to good local minima of a non-convex cost function. To overcome the severe coupling restrictions between physical qubits on the D-Wave Chimera graph, we use embedding tools to achieve approximately all-to-all connectivity across a reduced number of logical qubits. We assess the sparse representations generated by the D-Wave using both the total energy as well as classification accuracy on a subset of the CIFAR-10 database. The D-Wave 2X outperforms two classical state-of-the-art binary solvers, GUROBI and Chimera-inspired algorithm Hamze-Freitas-Selby (HFS). Specifically, the D-Wave 2X yields lower energy sparse solutions within seconds while the largest problems take over 10 hours for both GUROBI and HFS. We obtained cross-validation classification of 31.02% for the first 4K images using 47 features on the quantum D- Wave 2X." @default.
- W2771920568 created "2017-12-22" @default.
- W2771920568 creator A5065112326 @default.
- W2771920568 creator A5083800945 @default.
- W2771920568 creator A5086534835 @default.
- W2771920568 date "2017-11-01" @default.
- W2771920568 modified "2023-09-27" @default.
- W2771920568 title "Generating Sparse Representations Using Quantum Annealing: Comparison to Classical Algorithms" @default.
- W2771920568 cites W2028781966 @default.
- W2771920568 cites W2100543212 @default.
- W2771920568 cites W2105464873 @default.
- W2771920568 cites W2145096794 @default.
- W2771920568 cites W2145889472 @default.
- W2771920568 cites W2153663612 @default.
- W2771920568 cites W3102392596 @default.
- W2771920568 cites W4250955649 @default.
- W2771920568 doi "https://doi.org/10.1109/icrc.2017.8123653" @default.
- W2771920568 hasPublicationYear "2017" @default.
- W2771920568 type Work @default.
- W2771920568 sameAs 2771920568 @default.
- W2771920568 citedByCount "4" @default.
- W2771920568 countsByYear W27719205682018 @default.
- W2771920568 countsByYear W27719205682020 @default.
- W2771920568 countsByYear W27719205682022 @default.
- W2771920568 crossrefType "proceedings-article" @default.
- W2771920568 hasAuthorship W2771920568A5065112326 @default.
- W2771920568 hasAuthorship W2771920568A5083800945 @default.
- W2771920568 hasAuthorship W2771920568A5086534835 @default.
- W2771920568 hasConcept C113603373 @default.
- W2771920568 hasConcept C11413529 @default.
- W2771920568 hasConcept C121332964 @default.
- W2771920568 hasConcept C126980161 @default.
- W2771920568 hasConcept C134306372 @default.
- W2771920568 hasConcept C154945302 @default.
- W2771920568 hasConcept C177179195 @default.
- W2771920568 hasConcept C186633575 @default.
- W2771920568 hasConcept C203087015 @default.
- W2771920568 hasConcept C33923547 @default.
- W2771920568 hasConcept C41008148 @default.
- W2771920568 hasConcept C58053490 @default.
- W2771920568 hasConcept C62520636 @default.
- W2771920568 hasConcept C84114770 @default.
- W2771920568 hasConceptScore W2771920568C113603373 @default.
- W2771920568 hasConceptScore W2771920568C11413529 @default.
- W2771920568 hasConceptScore W2771920568C121332964 @default.
- W2771920568 hasConceptScore W2771920568C126980161 @default.
- W2771920568 hasConceptScore W2771920568C134306372 @default.
- W2771920568 hasConceptScore W2771920568C154945302 @default.
- W2771920568 hasConceptScore W2771920568C177179195 @default.
- W2771920568 hasConceptScore W2771920568C186633575 @default.
- W2771920568 hasConceptScore W2771920568C203087015 @default.
- W2771920568 hasConceptScore W2771920568C33923547 @default.
- W2771920568 hasConceptScore W2771920568C41008148 @default.
- W2771920568 hasConceptScore W2771920568C58053490 @default.
- W2771920568 hasConceptScore W2771920568C62520636 @default.
- W2771920568 hasConceptScore W2771920568C84114770 @default.
- W2771920568 hasLocation W27719205681 @default.
- W2771920568 hasOpenAccess W2771920568 @default.
- W2771920568 hasPrimaryLocation W27719205681 @default.
- W2771920568 hasRelatedWork W1507545366 @default.
- W2771920568 hasRelatedWork W1985522282 @default.
- W2771920568 hasRelatedWork W2050323428 @default.
- W2771920568 hasRelatedWork W2472799527 @default.
- W2771920568 hasRelatedWork W2963048504 @default.
- W2771920568 hasRelatedWork W2979900679 @default.
- W2771920568 hasRelatedWork W3122201086 @default.
- W2771920568 hasRelatedWork W3127384664 @default.
- W2771920568 hasRelatedWork W3208261700 @default.
- W2771920568 hasRelatedWork W4200327767 @default.
- W2771920568 isParatext "false" @default.
- W2771920568 isRetracted "false" @default.
- W2771920568 magId "2771920568" @default.
- W2771920568 workType "article" @default.