Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220824231> ?p ?o ?g. }
- W4220824231 endingPage "20" @default.
- W4220824231 startingPage "1" @default.
- W4220824231 abstract "This work addresses how to naturally adopt the l 2 -norm cosine similarity in the neuromemristive system and studies the unsupervised learning performance on handwritten digit image recognition. Proposed architecture is a two-layer fully connected neural network with a hard winner-take-all (WTA) learning module. For input layer, we propose single-spike temporal code that transforms input stimuli into the set of single spikes with different latencies and voltage levels. For a synapse model, we employ a compound memristor where stochastically switching binary-state memristors connected in parallel, which offers a reliable and scalable multi-state solution for synaptic weight storage. Hardware-friendly synaptic adaptation mechanism is proposed to realize spike-timing-dependent plasticity learning. Input spikes are sent out through those memristive synapses to each and every integrate-and-fire neuron in the fully connected output layer, where the hard WTA network motif introduces the competition based on cosine similarity for the given input stimuli. Finally, we present 92.64% accuracy performance on unsupervised digit recognition with only single-epoch MNIST dataset training via high-level simulations, including extensive analysis on the impact of system parameters." @default.
- W4220824231 created "2022-04-03" @default.
- W4220824231 creator A5009921171 @default.
- W4220824231 creator A5027587692 @default.
- W4220824231 creator A5033784578 @default.
- W4220824231 creator A5041659450 @default.
- W4220824231 creator A5047248181 @default.
- W4220824231 creator A5055180697 @default.
- W4220824231 creator A5071645986 @default.
- W4220824231 creator A5089860537 @default.
- W4220824231 date "2022-03-10" @default.
- W4220824231 modified "2023-09-23" @default.
- W4220824231 title "Unsupervised Digit Recognition Using Cosine Similarity In A Neuromemristive Competitive Learning System" @default.
- W4220824231 cites W1570411240 @default.
- W4220824231 cites W1594210692 @default.
- W4220824231 cites W1673584506 @default.
- W4220824231 cites W1843946745 @default.
- W4220824231 cites W1970974872 @default.
- W4220824231 cites W1976903415 @default.
- W4220824231 cites W1977765713 @default.
- W4220824231 cites W1979879449 @default.
- W4220824231 cites W1981484129 @default.
- W4220824231 cites W2007815184 @default.
- W4220824231 cites W2016922062 @default.
- W4220824231 cites W2020285738 @default.
- W4220824231 cites W2023698363 @default.
- W4220824231 cites W2030568691 @default.
- W4220824231 cites W2078835982 @default.
- W4220824231 cites W2092462444 @default.
- W4220824231 cites W2102875151 @default.
- W4220824231 cites W2110654393 @default.
- W4220824231 cites W2127388521 @default.
- W4220824231 cites W2132385194 @default.
- W4220824231 cites W2134539886 @default.
- W4220824231 cites W2143483829 @default.
- W4220824231 cites W2162827630 @default.
- W4220824231 cites W2163630896 @default.
- W4220824231 cites W2171888576 @default.
- W4220824231 cites W2187011629 @default.
- W4220824231 cites W2198142417 @default.
- W4220824231 cites W2245173025 @default.
- W4220824231 cites W2261105975 @default.
- W4220824231 cites W2399958287 @default.
- W4220824231 cites W2401075645 @default.
- W4220824231 cites W2433248078 @default.
- W4220824231 cites W2487018225 @default.
- W4220824231 cites W2532561498 @default.
- W4220824231 cites W2556583623 @default.
- W4220824231 cites W2559718113 @default.
- W4220824231 cites W2560615381 @default.
- W4220824231 cites W2594833348 @default.
- W4220824231 cites W2605663629 @default.
- W4220824231 cites W2606722458 @default.
- W4220824231 cites W2621466894 @default.
- W4220824231 cites W2743001015 @default.
- W4220824231 cites W2778935320 @default.
- W4220824231 cites W2790604742 @default.
- W4220824231 cites W2802063747 @default.
- W4220824231 cites W2805403707 @default.
- W4220824231 cites W2810068957 @default.
- W4220824231 cites W2883283267 @default.
- W4220824231 cites W2902404732 @default.
- W4220824231 cites W2903590539 @default.
- W4220824231 cites W2931141826 @default.
- W4220824231 cites W2964317776 @default.
- W4220824231 cites W3035927999 @default.
- W4220824231 cites W3092108775 @default.
- W4220824231 cites W3101227480 @default.
- W4220824231 cites W4232220759 @default.
- W4220824231 cites W4248918913 @default.
- W4220824231 doi "https://doi.org/10.1145/3473036" @default.
- W4220824231 hasPublicationYear "2022" @default.
- W4220824231 type Work @default.
- W4220824231 citedByCount "0" @default.
- W4220824231 crossrefType "journal-article" @default.
- W4220824231 hasAuthorship W4220824231A5009921171 @default.
- W4220824231 hasAuthorship W4220824231A5027587692 @default.
- W4220824231 hasAuthorship W4220824231A5033784578 @default.
- W4220824231 hasAuthorship W4220824231A5041659450 @default.
- W4220824231 hasAuthorship W4220824231A5047248181 @default.
- W4220824231 hasAuthorship W4220824231A5055180697 @default.
- W4220824231 hasAuthorship W4220824231A5071645986 @default.
- W4220824231 hasAuthorship W4220824231A5089860537 @default.
- W4220824231 hasConcept C11731999 @default.
- W4220824231 hasConcept C120822770 @default.
- W4220824231 hasConcept C127413603 @default.
- W4220824231 hasConcept C150072547 @default.
- W4220824231 hasConcept C153180895 @default.
- W4220824231 hasConcept C154945302 @default.
- W4220824231 hasConcept C168976158 @default.
- W4220824231 hasConcept C190502265 @default.
- W4220824231 hasConcept C24326235 @default.
- W4220824231 hasConcept C2779127903 @default.
- W4220824231 hasConcept C41008148 @default.
- W4220824231 hasConcept C50644808 @default.
- W4220824231 hasConcept C8038995 @default.
- W4220824231 hasConceptScore W4220824231C11731999 @default.
- W4220824231 hasConceptScore W4220824231C120822770 @default.