TY - GEN
T1 - Online unsupervised structural plasticity algorithm for multi-layer Winner-Take-All with binary synapses
AU - Roy, Subhrajit
AU - Tong, He
AU - Basu, Arindam
N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].
PY - 2017/1/23
Y1 - 2017/1/23
N2 - This article introduces a novel hardware friendly multi-layer Winner-Take-All (WTA) architecture using neurons with nonlinear dendrites and binary synapses. The network is trained by an unsupervised spike based learning rule that modifies the network connections. Inspired by the multi-layer models of human visual cortex, the proposed architecture contains multiple layers of neurons. We show that if we increase the synaptic time constant of the layers of the system in succession, it is capable of inspecting the incoming patterns for a longer duration of time before providing a decision. After the training is complete, a unique neuron of the last layer emits a spike for same class of patterns. The results discussed in this article show that the proposed structural plasticity based WTA is capable of classifying Poisson spike trains and the two layer structure provides a 2% and a 38% increase in performance for two different tasks when sufficient neurons are employed. Moreover, compared to conventional architectures, our method is far more memory efficient for high dimensional inputs (input dimension > 200).
AB - This article introduces a novel hardware friendly multi-layer Winner-Take-All (WTA) architecture using neurons with nonlinear dendrites and binary synapses. The network is trained by an unsupervised spike based learning rule that modifies the network connections. Inspired by the multi-layer models of human visual cortex, the proposed architecture contains multiple layers of neurons. We show that if we increase the synaptic time constant of the layers of the system in succession, it is capable of inspecting the incoming patterns for a longer duration of time before providing a decision. After the training is complete, a unique neuron of the last layer emits a spike for same class of patterns. The results discussed in this article show that the proposed structural plasticity based WTA is capable of classifying Poisson spike trains and the two layer structure provides a 2% and a 38% increase in performance for two different tasks when sufficient neurons are employed. Moreover, compared to conventional architectures, our method is far more memory efficient for high dimensional inputs (input dimension > 200).
UR - https://www.scopus.com/pages/publications/85013847670
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85013847670&origin=recordpage
U2 - 10.1109/ISICIR.2016.7829691
DO - 10.1109/ISICIR.2016.7829691
M3 - RGC 32 - Refereed conference paper (with host publication)
SN - 9781467390194
T3 - 2016 International Symposium on Integrated Circuits, ISIC 2016
BT - 2016 International Symposium on Integrated Circuits, ISIC 2016
PB - IEEE
T2 - 2016 International Symposium on Integrated Circuits, ISIC 2016
Y2 - 12 December 2016 through 14 December 2016
ER -