Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381682834> ?p ?o ?g. }
- W4381682834 abstract "The backpropagation algorithm has promoted the rapid development of deep learning, but it relies on a large amount of labeled data and still has a large gap with how humans learn. The human brain can quickly learn various conceptual knowledge in a self-organized and unsupervised manner, accomplished through coordinating various learning rules and structures in the human brain. Spike-timing-dependent plasticity (STDP) is a general learning rule in the brain, but spiking neural networks (SNNs) trained with STDP alone is inefficient and perform poorly. In this paper, taking inspiration from short-term synaptic plasticity, we design an adaptive synaptic filter and introduce the adaptive spiking threshold as the neuron plasticity to enrich the representation ability of SNNs. We also introduce an adaptive lateral inhibitory connection to adjust the spikes balance dynamically to help the network learn richer features. To speed up and stabilize the training of unsupervised spiking neural networks, we design a samples temporal batch STDP (STB-STDP), which updates weights based on multiple samples and moments. By integrating the above three adaptive mechanisms and STB-STDP, our model greatly accelerates the training of unsupervised spiking neural networks and improves the performance of unsupervised SNNs on complex tasks. Our model achieves the current state-of-the-art performance of unsupervised STDP-based SNNs in the MNIST and FashionMNIST datasets. Further, we tested on the more complex CIFAR10 dataset, and the results fully illustrate the superiority of our algorithm. Our model is also the first work to apply unsupervised STDP-based SNNs to CIFAR10. At the same time, in the small-sample learning scenario, it will far exceed the supervised ANN using the same structure." @default.
- W4381682834 created "2023-06-23" @default.
- W4381682834 creator A5025846619 @default.
- W4381682834 creator A5048906374 @default.
- W4381682834 creator A5064842058 @default.
- W4381682834 creator A5091698766 @default.
- W4381682834 date "2023-06-01" @default.
- W4381682834 modified "2023-09-30" @default.
- W4381682834 title "An unsupervised STDP-based spiking neural network inspired by biologically plausible learning rules and connections" @default.
- W4381682834 cites W101771737 @default.
- W4381682834 cites W1570411240 @default.
- W4381682834 cites W2029374903 @default.
- W4381682834 cites W2037798038 @default.
- W4381682834 cites W2047578520 @default.
- W4381682834 cites W2056220030 @default.
- W4381682834 cites W2084259975 @default.
- W4381682834 cites W2093643893 @default.
- W4381682834 cites W2094048200 @default.
- W4381682834 cites W2112796928 @default.
- W4381682834 cites W2112927743 @default.
- W4381682834 cites W2136235652 @default.
- W4381682834 cites W2141114982 @default.
- W4381682834 cites W2147101007 @default.
- W4381682834 cites W2159271282 @default.
- W4381682834 cites W2162827630 @default.
- W4381682834 cites W2212384750 @default.
- W4381682834 cites W2432549741 @default.
- W4381682834 cites W2513853720 @default.
- W4381682834 cites W2552737632 @default.
- W4381682834 cites W2621826044 @default.
- W4381682834 cites W2779025322 @default.
- W4381682834 cites W2787907153 @default.
- W4381682834 cites W2796323669 @default.
- W4381682834 cites W2808550672 @default.
- W4381682834 cites W2892077605 @default.
- W4381682834 cites W2905533880 @default.
- W4381682834 cites W2946092987 @default.
- W4381682834 cites W2963206832 @default.
- W4381682834 cites W3004852569 @default.
- W4381682834 cites W3035000326 @default.
- W4381682834 cites W3109080038 @default.
- W4381682834 cites W3118900089 @default.
- W4381682834 cites W3128872541 @default.
- W4381682834 cites W3131336557 @default.
- W4381682834 cites W3211954089 @default.
- W4381682834 cites W4242770316 @default.
- W4381682834 cites W4247763225 @default.
- W4381682834 doi "https://doi.org/10.1016/j.neunet.2023.06.019" @default.
- W4381682834 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37418862" @default.
- W4381682834 hasPublicationYear "2023" @default.
- W4381682834 type Work @default.
- W4381682834 citedByCount "2" @default.
- W4381682834 countsByYear W43816828342023 @default.
- W4381682834 crossrefType "journal-article" @default.
- W4381682834 hasAuthorship W4381682834A5025846619 @default.
- W4381682834 hasAuthorship W4381682834A5048906374 @default.
- W4381682834 hasAuthorship W4381682834A5064842058 @default.
- W4381682834 hasAuthorship W4381682834A5091698766 @default.
- W4381682834 hasBestOaLocation W43816828341 @default.
- W4381682834 hasConcept C11731999 @default.
- W4381682834 hasConcept C119857082 @default.
- W4381682834 hasConcept C120822770 @default.
- W4381682834 hasConcept C153180895 @default.
- W4381682834 hasConcept C154945302 @default.
- W4381682834 hasConcept C159919123 @default.
- W4381682834 hasConcept C170493617 @default.
- W4381682834 hasConcept C185592680 @default.
- W4381682834 hasConcept C190502265 @default.
- W4381682834 hasConcept C41008148 @default.
- W4381682834 hasConcept C50644808 @default.
- W4381682834 hasConcept C55493867 @default.
- W4381682834 hasConcept C8038995 @default.
- W4381682834 hasConcept C98229152 @default.
- W4381682834 hasConceptScore W4381682834C11731999 @default.
- W4381682834 hasConceptScore W4381682834C119857082 @default.
- W4381682834 hasConceptScore W4381682834C120822770 @default.
- W4381682834 hasConceptScore W4381682834C153180895 @default.
- W4381682834 hasConceptScore W4381682834C154945302 @default.
- W4381682834 hasConceptScore W4381682834C159919123 @default.
- W4381682834 hasConceptScore W4381682834C170493617 @default.
- W4381682834 hasConceptScore W4381682834C185592680 @default.
- W4381682834 hasConceptScore W4381682834C190502265 @default.
- W4381682834 hasConceptScore W4381682834C41008148 @default.
- W4381682834 hasConceptScore W4381682834C50644808 @default.
- W4381682834 hasConceptScore W4381682834C55493867 @default.
- W4381682834 hasConceptScore W4381682834C8038995 @default.
- W4381682834 hasConceptScore W4381682834C98229152 @default.
- W4381682834 hasLocation W43816828341 @default.
- W4381682834 hasLocation W43816828342 @default.
- W4381682834 hasOpenAccess W4381682834 @default.
- W4381682834 hasPrimaryLocation W43816828341 @default.
- W4381682834 hasRelatedWork W2556793986 @default.
- W4381682834 hasRelatedWork W2952868231 @default.
- W4381682834 hasRelatedWork W2960894448 @default.
- W4381682834 hasRelatedWork W3154516076 @default.
- W4381682834 hasRelatedWork W4214864280 @default.
- W4381682834 hasRelatedWork W4284883759 @default.
- W4381682834 hasRelatedWork W4362654310 @default.
- W4381682834 hasRelatedWork W4381682834 @default.
- W4381682834 hasRelatedWork W4383501663 @default.