Matches in SemOpenAlex for { <https://semopenalex.org/work/W3203040596> ?p ?o ?g. }
- W3203040596 endingPage "7067" @default.
- W3203040596 startingPage "7059" @default.
- W3203040596 abstract "Spiking neural networks (SNNs) can be run on neuromorphic devices with ultra-high speed and ultra-low energy consumption because of their binary and event-driven nature. Therefore, SNNs are expected to have various applications, including as generative models being running on edge devices to create high-quality images. In this study, we build a variational autoencoder (VAE) with SNN to enable image generation. VAE is known for its stability among generative models; recently, its quality advanced. In vanilla VAE, the latent space is represented as a normal distribution, and floating-point calculations are required in sampling. However, this is not possible in SNNs because all features must be binary time series data. Therefore, we constructed the latent space with an autoregressive SNN model, and randomly selected samples from its output to sample the latent variables. This allows the latent variables to follow the Bernoulli process and allows variational learning. Thus, we build the Fully Spiking Variational Autoencoder where all modules are constructed with SNN. To the best of our knowledge, we are the first to build a VAE only with SNN layers. We experimented with several datasets, and confirmed that it can generate images with the same or better quality compared to conventional ANNs. The code is available at https://github.com/kamata1729/FullySpikingVAE." @default.
- W3203040596 created "2021-10-11" @default.
- W3203040596 creator A5016681039 @default.
- W3203040596 creator A5042711470 @default.
- W3203040596 creator A5061625131 @default.
- W3203040596 date "2022-06-28" @default.
- W3203040596 modified "2023-09-30" @default.
- W3203040596 title "Fully Spiking Variational Autoencoder" @default.
- W3203040596 cites W1479903351 @default.
- W3203040596 cites W1570411240 @default.
- W3203040596 cites W1604973310 @default.
- W3203040596 cites W1834627138 @default.
- W3203040596 cites W1959608418 @default.
- W3203040596 cites W1996336919 @default.
- W3203040596 cites W2016589492 @default.
- W3203040596 cites W2064675550 @default.
- W3203040596 cites W2088915398 @default.
- W3203040596 cites W2108598243 @default.
- W3203040596 cites W2130360162 @default.
- W3203040596 cites W2155212997 @default.
- W3203040596 cites W2182396527 @default.
- W3203040596 cites W2341783944 @default.
- W3203040596 cites W2765229157 @default.
- W3203040596 cites W2775079417 @default.
- W3203040596 cites W2783525259 @default.
- W3203040596 cites W2901937441 @default.
- W3203040596 cites W2908510526 @default.
- W3203040596 cites W2963373786 @default.
- W3203040596 cites W2963760575 @default.
- W3203040596 cites W2963799213 @default.
- W3203040596 cites W2963981733 @default.
- W3203040596 cites W2970971581 @default.
- W3203040596 cites W2971074500 @default.
- W3203040596 cites W2989578727 @default.
- W3203040596 cites W3035574324 @default.
- W3203040596 cites W3092083701 @default.
- W3203040596 cites W3098510582 @default.
- W3203040596 cites W3099451594 @default.
- W3203040596 cites W3100019421 @default.
- W3203040596 cites W3102087395 @default.
- W3203040596 cites W3118608800 @default.
- W3203040596 cites W3142770901 @default.
- W3203040596 cites W3153872861 @default.
- W3203040596 cites W3169841020 @default.
- W3203040596 cites W3177133146 @default.
- W3203040596 cites W592244745 @default.
- W3203040596 cites W648786980 @default.
- W3203040596 cites W2006370340 @default.
- W3203040596 cites W3153854932 @default.
- W3203040596 doi "https://doi.org/10.1609/aaai.v36i6.20665" @default.
- W3203040596 hasPublicationYear "2022" @default.
- W3203040596 type Work @default.
- W3203040596 sameAs 3203040596 @default.
- W3203040596 citedByCount "1" @default.
- W3203040596 countsByYear W32030405962023 @default.
- W3203040596 crossrefType "journal-article" @default.
- W3203040596 hasAuthorship W3203040596A5016681039 @default.
- W3203040596 hasAuthorship W3203040596A5042711470 @default.
- W3203040596 hasAuthorship W3203040596A5061625131 @default.
- W3203040596 hasBestOaLocation W32030405961 @default.
- W3203040596 hasConcept C101738243 @default.
- W3203040596 hasConcept C105795698 @default.
- W3203040596 hasConcept C112972136 @default.
- W3203040596 hasConcept C11413529 @default.
- W3203040596 hasConcept C11731999 @default.
- W3203040596 hasConcept C119857082 @default.
- W3203040596 hasConcept C121332964 @default.
- W3203040596 hasConcept C127413603 @default.
- W3203040596 hasConcept C146978453 @default.
- W3203040596 hasConcept C152361515 @default.
- W3203040596 hasConcept C153180895 @default.
- W3203040596 hasConcept C154945302 @default.
- W3203040596 hasConcept C159877910 @default.
- W3203040596 hasConcept C23990920 @default.
- W3203040596 hasConcept C2779662365 @default.
- W3203040596 hasConcept C33923547 @default.
- W3203040596 hasConcept C41008148 @default.
- W3203040596 hasConcept C48372109 @default.
- W3203040596 hasConcept C50644808 @default.
- W3203040596 hasConcept C51167844 @default.
- W3203040596 hasConcept C62520636 @default.
- W3203040596 hasConcept C94375191 @default.
- W3203040596 hasConceptScore W3203040596C101738243 @default.
- W3203040596 hasConceptScore W3203040596C105795698 @default.
- W3203040596 hasConceptScore W3203040596C112972136 @default.
- W3203040596 hasConceptScore W3203040596C11413529 @default.
- W3203040596 hasConceptScore W3203040596C11731999 @default.
- W3203040596 hasConceptScore W3203040596C119857082 @default.
- W3203040596 hasConceptScore W3203040596C121332964 @default.
- W3203040596 hasConceptScore W3203040596C127413603 @default.
- W3203040596 hasConceptScore W3203040596C146978453 @default.
- W3203040596 hasConceptScore W3203040596C152361515 @default.
- W3203040596 hasConceptScore W3203040596C153180895 @default.
- W3203040596 hasConceptScore W3203040596C154945302 @default.
- W3203040596 hasConceptScore W3203040596C159877910 @default.
- W3203040596 hasConceptScore W3203040596C23990920 @default.
- W3203040596 hasConceptScore W3203040596C2779662365 @default.
- W3203040596 hasConceptScore W3203040596C33923547 @default.