Matches in SemOpenAlex for { <https://semopenalex.org/work/W2765091082> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W2765091082 abstract "Restricted Boltzmann Machine (RBM) is the building block of Deep Belief Nets and other deep learning tools. Fast learning and prediction are both essential for practical usage of RBM-based machine learning techniques. This paper presents a concept named generalized redundancy elimination to avoid most of the the computations required in RBM learning and prediction without changing the results. It consists of two optimization techniques. The first is called bounds-based filtering, which, through triangular inequality, replaces expensive calculations of many vector dot products with fast bounds calculations. The second is delta product, which effectively detects and avoids many repeated calculations in the core operation of RBM, Gibbs Sampling. The optimizations are applicable to both the standard contrastive divergence learning algorithm and its variations. In addition, the paper presents how to address some complexities these optimizations create for them to be used together and for them to be implemented efficiently on massively parallel processors. Results show that the optimizations can produce several-fold (up to 3X for training and 5.3X for prediction) speedups." @default.
- W2765091082 created "2017-11-10" @default.
- W2765091082 creator A5012435102 @default.
- W2765091082 creator A5027034307 @default.
- W2765091082 creator A5028760405 @default.
- W2765091082 date "2017-09-01" @default.
- W2765091082 modified "2023-10-03" @default.
- W2765091082 title "POSTER: Cutting the Fat: Speeding Up RBM for Fast Deep Learning Through Generalized Redundancy Elimination" @default.
- W2765091082 cites W2116825644 @default.
- W2765091082 cites W44815768 @default.
- W2765091082 doi "https://doi.org/10.1109/pact.2017.36" @default.
- W2765091082 hasPublicationYear "2017" @default.
- W2765091082 type Work @default.
- W2765091082 sameAs 2765091082 @default.
- W2765091082 citedByCount "1" @default.
- W2765091082 countsByYear W27650910822019 @default.
- W2765091082 crossrefType "proceedings-article" @default.
- W2765091082 hasAuthorship W2765091082A5012435102 @default.
- W2765091082 hasAuthorship W2765091082A5027034307 @default.
- W2765091082 hasAuthorship W2765091082A5028760405 @default.
- W2765091082 hasConcept C108583219 @default.
- W2765091082 hasConcept C111919701 @default.
- W2765091082 hasConcept C11413529 @default.
- W2765091082 hasConcept C119857082 @default.
- W2765091082 hasConcept C152124472 @default.
- W2765091082 hasConcept C154945302 @default.
- W2765091082 hasConcept C173608175 @default.
- W2765091082 hasConcept C192576344 @default.
- W2765091082 hasConcept C199354608 @default.
- W2765091082 hasConcept C41008148 @default.
- W2765091082 hasConcept C45374587 @default.
- W2765091082 hasConcept C80444323 @default.
- W2765091082 hasConceptScore W2765091082C108583219 @default.
- W2765091082 hasConceptScore W2765091082C111919701 @default.
- W2765091082 hasConceptScore W2765091082C11413529 @default.
- W2765091082 hasConceptScore W2765091082C119857082 @default.
- W2765091082 hasConceptScore W2765091082C152124472 @default.
- W2765091082 hasConceptScore W2765091082C154945302 @default.
- W2765091082 hasConceptScore W2765091082C173608175 @default.
- W2765091082 hasConceptScore W2765091082C192576344 @default.
- W2765091082 hasConceptScore W2765091082C199354608 @default.
- W2765091082 hasConceptScore W2765091082C41008148 @default.
- W2765091082 hasConceptScore W2765091082C45374587 @default.
- W2765091082 hasConceptScore W2765091082C80444323 @default.
- W2765091082 hasLocation W27650910821 @default.
- W2765091082 hasOpenAccess W2765091082 @default.
- W2765091082 hasPrimaryLocation W27650910821 @default.
- W2765091082 hasRelatedWork W1481131999 @default.
- W2765091082 hasRelatedWork W1934946603 @default.
- W2765091082 hasRelatedWork W2013928556 @default.
- W2765091082 hasRelatedWork W2231586635 @default.
- W2765091082 hasRelatedWork W2547440996 @default.
- W2765091082 hasRelatedWork W2564159225 @default.
- W2765091082 hasRelatedWork W2900214122 @default.
- W2765091082 hasRelatedWork W2944280939 @default.
- W2765091082 hasRelatedWork W2980402699 @default.
- W2765091082 hasRelatedWork W2988666181 @default.
- W2765091082 hasRelatedWork W3037432796 @default.
- W2765091082 hasRelatedWork W3037888750 @default.
- W2765091082 hasRelatedWork W3082046152 @default.
- W2765091082 hasRelatedWork W3136054432 @default.
- W2765091082 hasRelatedWork W3136941290 @default.
- W2765091082 hasRelatedWork W3157202145 @default.
- W2765091082 hasRelatedWork W3187677057 @default.
- W2765091082 hasRelatedWork W3195294617 @default.
- W2765091082 hasRelatedWork W3205805162 @default.
- W2765091082 hasRelatedWork W94363386 @default.
- W2765091082 isParatext "false" @default.
- W2765091082 isRetracted "false" @default.
- W2765091082 magId "2765091082" @default.
- W2765091082 workType "article" @default.