TY - CHAP
T1 - Temporal learning in multilayer spiking neural networks through construction of causal connections
AU - Yu, Qiang
AU - Tang, Huajin
AU - Hu, Jun
AU - Tan, Kay Chen
PY - 2017/5
Y1 - 2017/5
N2 - This chapter presents a new supervised temporal learning rule for multilayer spiking neural networks. We present and analyze the mechanisms utilized in the network for the construction of causal connections. Synaptic efficacies are finely tuned for resulting in a desired post-synaptic firing status. Both the PSD rule and the tempotron rule are extended to multiple layers, leading to new rules of multilayer PSD (MutPSD) and multilayer tempotron (MutTmptr). The algorithms are applied successfully to classic linearly non-separable benchmarks like the XOR and the Iris problems.
AB - This chapter presents a new supervised temporal learning rule for multilayer spiking neural networks. We present and analyze the mechanisms utilized in the network for the construction of causal connections. Synaptic efficacies are finely tuned for resulting in a desired post-synaptic firing status. Both the PSD rule and the tempotron rule are extended to multiple layers, leading to new rules of multilayer PSD (MutPSD) and multilayer tempotron (MutTmptr). The algorithms are applied successfully to classic linearly non-separable benchmarks like the XOR and the Iris problems.
UR - http://www.scopus.com/inward/record.url?scp=85019130292&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85019130292&origin=recordpage
U2 - 10.1007/978-3-319-55310-8_6
DO - 10.1007/978-3-319-55310-8_6
M3 - RGC 12 - Chapter in an edited book (Author)
VL - 126
T3 - Intelligent Systems Reference Library
SP - 115
EP - 129
BT - Neuromorphic Cognitive Systems
PB - Springer Science and Business Media Deutschland GmbH
ER -