Matches in SemOpenAlex for { <https://semopenalex.org/work/W2552932458> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W2552932458 abstract "Biological brains exhibit a remarkable capacity to recognise real-world patterns effectively. Despite major advances in neuroscience over the last few decades, an understanding of the brain's underlying mechanisms for pattern recognition remains unattained. Efforts to replicate such high-level brain functions on the basis of the limited, low-level known details of the brain have naturally led to critical assumptions that make brain-inspired machine learning possible. Convolutional neural networks are an example of such architectures, shown to produce state-of-the-art classification performance on practical applications. The Hierarchical Temporal Memory (HTM) model, on the other hand, performs pattern and sequence recognition on the basis of highly biologically plausible structure and operation. In this work we build on the strengths of convolutional neural networks by integrating them into the HTM framework. An analysis of the common and complementary features between the two models results in the proposal of an innovative, hybrid machine learning architecture. Practical tests on a handwritten digit recognition task reveal a 2% fall in pattern recognition performance, compared to that of the original convolutional neural network design. Nevertheless, key HTM features embedded in the novel architecture enable its potential future enhancement with sequence learning and prediction, an inexistent capability in traditional convolutional neural networks." @default.
- W2552932458 created "2016-11-30" @default.
- W2552932458 creator A5000677611 @default.
- W2552932458 creator A5013048777 @default.
- W2552932458 date "2016-07-01" @default.
- W2552932458 modified "2023-09-24" @default.
- W2552932458 title "Integrating convolutional neural networks into a sparse distributed representation model based on mammalian cortical learning" @default.
- W2552932458 cites W1737787488 @default.
- W2552932458 cites W1755950513 @default.
- W2552932458 cites W1892402995 @default.
- W2552932458 cites W2072057046 @default.
- W2552932458 cites W2076063813 @default.
- W2552932458 cites W2112796928 @default.
- W2552932458 doi "https://doi.org/10.1109/ijcnn.2016.7727332" @default.
- W2552932458 hasPublicationYear "2016" @default.
- W2552932458 type Work @default.
- W2552932458 sameAs 2552932458 @default.
- W2552932458 citedByCount "0" @default.
- W2552932458 crossrefType "proceedings-article" @default.
- W2552932458 hasAuthorship W2552932458A5000677611 @default.
- W2552932458 hasAuthorship W2552932458A5013048777 @default.
- W2552932458 hasBestOaLocation W25529324582 @default.
- W2552932458 hasConcept C105795698 @default.
- W2552932458 hasConcept C108583219 @default.
- W2552932458 hasConcept C119857082 @default.
- W2552932458 hasConcept C153180895 @default.
- W2552932458 hasConcept C154945302 @default.
- W2552932458 hasConcept C17744445 @default.
- W2552932458 hasConcept C199539241 @default.
- W2552932458 hasConcept C2776359362 @default.
- W2552932458 hasConcept C2781162219 @default.
- W2552932458 hasConcept C33923547 @default.
- W2552932458 hasConcept C41008148 @default.
- W2552932458 hasConcept C50644808 @default.
- W2552932458 hasConcept C81363708 @default.
- W2552932458 hasConcept C94625758 @default.
- W2552932458 hasConceptScore W2552932458C105795698 @default.
- W2552932458 hasConceptScore W2552932458C108583219 @default.
- W2552932458 hasConceptScore W2552932458C119857082 @default.
- W2552932458 hasConceptScore W2552932458C153180895 @default.
- W2552932458 hasConceptScore W2552932458C154945302 @default.
- W2552932458 hasConceptScore W2552932458C17744445 @default.
- W2552932458 hasConceptScore W2552932458C199539241 @default.
- W2552932458 hasConceptScore W2552932458C2776359362 @default.
- W2552932458 hasConceptScore W2552932458C2781162219 @default.
- W2552932458 hasConceptScore W2552932458C33923547 @default.
- W2552932458 hasConceptScore W2552932458C41008148 @default.
- W2552932458 hasConceptScore W2552932458C50644808 @default.
- W2552932458 hasConceptScore W2552932458C81363708 @default.
- W2552932458 hasConceptScore W2552932458C94625758 @default.
- W2552932458 hasLocation W25529324581 @default.
- W2552932458 hasLocation W25529324582 @default.
- W2552932458 hasOpenAccess W2552932458 @default.
- W2552932458 hasPrimaryLocation W25529324581 @default.
- W2552932458 hasRelatedWork W1556262934 @default.
- W2552932458 hasRelatedWork W1674129765 @default.
- W2552932458 hasRelatedWork W1797002335 @default.
- W2552932458 hasRelatedWork W1806868888 @default.
- W2552932458 hasRelatedWork W1932579912 @default.
- W2552932458 hasRelatedWork W2030168984 @default.
- W2552932458 hasRelatedWork W2030214242 @default.
- W2552932458 hasRelatedWork W2045974126 @default.
- W2552932458 hasRelatedWork W2046738549 @default.
- W2552932458 hasRelatedWork W2052358995 @default.
- W2552932458 hasRelatedWork W2084219467 @default.
- W2552932458 hasRelatedWork W2098913372 @default.
- W2552932458 hasRelatedWork W2105340575 @default.
- W2552932458 hasRelatedWork W2121648484 @default.
- W2552932458 hasRelatedWork W2171218275 @default.
- W2552932458 hasRelatedWork W2540299398 @default.
- W2552932458 hasRelatedWork W2545848684 @default.
- W2552932458 hasRelatedWork W2770108382 @default.
- W2552932458 hasRelatedWork W305083097 @default.
- W2552932458 hasRelatedWork W3092663764 @default.
- W2552932458 isParatext "false" @default.
- W2552932458 isRetracted "false" @default.
- W2552932458 magId "2552932458" @default.
- W2552932458 workType "article" @default.