Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286585373> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4286585373 abstract "A hybrid quantum-classical method for learning Boltzmann machines (BM) for a generative and discriminative task is presented. Boltzmann machines are undirected graphs with a network of visible and hidden nodes where the former is used as the reading site while the latter is used to manipulate visible states' probability. In Generative BM, the samples of visible data imitate the probability distribution of a given data set. In contrast, the visible sites of discriminative BM are treated as Input/Output (I/O) reading sites where the conditional probability of output state is optimized for a given set of input states. The cost function for learning BM is defined as a weighted sum of Kullback-Leibler (KL) divergence and Negative conditional Log-Likelihood (NCLL), adjusted using a hyperparamter. Here, the KL Divergence is the cost for generative learning, and NCLL is the cost for discriminative learning. A Stochastic Newton-Raphson optimization scheme is presented. The gradients and the Hessians are approximated using direct samples of BM obtained through Quantum annealing (QA). Quantum annealers are hardware representing the physics of the Ising model that operates on low but finite temperature. This temperature affects the probability distribution of the BM; however, its value is unknown. Previous efforts have focused on estimating this unknown temperature through regression of theoretical Boltzmann energies of sampled states with the probability of states sampled by the actual hardware. This assumes that the control parameter change does not affect the system temperature, however, this is not usually the case. Instead, an approach that works on the probability distribution of samples, instead of the energies, is proposed to estimate the optimal parameter set. This ensures that the optimal set can be obtained from a single run." @default.
- W4286585373 created "2022-07-22" @default.
- W4286585373 creator A5006013675 @default.
- W4286585373 creator A5061179588 @default.
- W4286585373 date "2020-02-03" @default.
- W4286585373 modified "2023-09-28" @default.
- W4286585373 title "Generative and discriminative training of Boltzmann machine through Quantum annealing" @default.
- W4286585373 doi "https://doi.org/10.48550/arxiv.2002.00792" @default.
- W4286585373 hasPublicationYear "2020" @default.
- W4286585373 type Work @default.
- W4286585373 citedByCount "0" @default.
- W4286585373 crossrefType "posted-content" @default.
- W4286585373 hasAuthorship W4286585373A5006013675 @default.
- W4286585373 hasAuthorship W4286585373A5061179588 @default.
- W4286585373 hasBestOaLocation W42865853731 @default.
- W4286585373 hasConcept C105795698 @default.
- W4286585373 hasConcept C11413529 @default.
- W4286585373 hasConcept C121332964 @default.
- W4286585373 hasConcept C121864883 @default.
- W4286585373 hasConcept C126980161 @default.
- W4286585373 hasConcept C138885662 @default.
- W4286585373 hasConcept C149441793 @default.
- W4286585373 hasConcept C154945302 @default.
- W4286585373 hasConcept C167966045 @default.
- W4286585373 hasConcept C171752962 @default.
- W4286585373 hasConcept C192576344 @default.
- W4286585373 hasConcept C193999330 @default.
- W4286585373 hasConcept C207390915 @default.
- W4286585373 hasConcept C33923547 @default.
- W4286585373 hasConcept C39890363 @default.
- W4286585373 hasConcept C41008148 @default.
- W4286585373 hasConcept C41895202 @default.
- W4286585373 hasConcept C43555835 @default.
- W4286585373 hasConcept C50644808 @default.
- W4286585373 hasConcept C97931131 @default.
- W4286585373 hasConceptScore W4286585373C105795698 @default.
- W4286585373 hasConceptScore W4286585373C11413529 @default.
- W4286585373 hasConceptScore W4286585373C121332964 @default.
- W4286585373 hasConceptScore W4286585373C121864883 @default.
- W4286585373 hasConceptScore W4286585373C126980161 @default.
- W4286585373 hasConceptScore W4286585373C138885662 @default.
- W4286585373 hasConceptScore W4286585373C149441793 @default.
- W4286585373 hasConceptScore W4286585373C154945302 @default.
- W4286585373 hasConceptScore W4286585373C167966045 @default.
- W4286585373 hasConceptScore W4286585373C171752962 @default.
- W4286585373 hasConceptScore W4286585373C192576344 @default.
- W4286585373 hasConceptScore W4286585373C193999330 @default.
- W4286585373 hasConceptScore W4286585373C207390915 @default.
- W4286585373 hasConceptScore W4286585373C33923547 @default.
- W4286585373 hasConceptScore W4286585373C39890363 @default.
- W4286585373 hasConceptScore W4286585373C41008148 @default.
- W4286585373 hasConceptScore W4286585373C41895202 @default.
- W4286585373 hasConceptScore W4286585373C43555835 @default.
- W4286585373 hasConceptScore W4286585373C50644808 @default.
- W4286585373 hasConceptScore W4286585373C97931131 @default.
- W4286585373 hasLocation W42865853731 @default.
- W4286585373 hasOpenAccess W4286585373 @default.
- W4286585373 hasPrimaryLocation W42865853731 @default.
- W4286585373 hasRelatedWork W12330997 @default.
- W4286585373 hasRelatedWork W1959568 @default.
- W4286585373 hasRelatedWork W2308079 @default.
- W4286585373 hasRelatedWork W2777938 @default.
- W4286585373 hasRelatedWork W5765193 @default.
- W4286585373 hasRelatedWork W6228540 @default.
- W4286585373 hasRelatedWork W699561 @default.
- W4286585373 hasRelatedWork W9190101 @default.
- W4286585373 hasRelatedWork W933276 @default.
- W4286585373 hasRelatedWork W9554121 @default.
- W4286585373 isParatext "false" @default.
- W4286585373 isRetracted "false" @default.
- W4286585373 workType "article" @default.