TY - GEN
T1 - Improved margin multi-class classification using dendritic neurons with morphological learning
AU - Hussain, Shaista
AU - Liu, Shih-Chii
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 - 2014
Y1 - 2014
N2 - We present an architecture of a spike based multiclass classifier using neurons with non-linear dendrites and sparse synaptic connectivity where each synapse takes a binary value. The learning in this model happens not through weight updates but through structural changes, i.e. a change of connectivity between inputs and dendrites. Hence, it is well suited for implementation in neuromorphic systems using address event representation (AER). We present a new learning rule that allows better generalization of the system to noisy testing data making it feasible to transfer learnt weights in software to a hardware device interfacing with noisy spiking sensors. The new rule improves testing accuracy by 7 - 10% compared to earlier versions. We also present preliminary results for multi-class classification on handwritten digits from the MNIST database and show that our system can attain comparable performance (≈ 3% more error) with other reported spike based classifiers while using at least 50% less synaptic resources. © 2014 IEEE.
AB - We present an architecture of a spike based multiclass classifier using neurons with non-linear dendrites and sparse synaptic connectivity where each synapse takes a binary value. The learning in this model happens not through weight updates but through structural changes, i.e. a change of connectivity between inputs and dendrites. Hence, it is well suited for implementation in neuromorphic systems using address event representation (AER). We present a new learning rule that allows better generalization of the system to noisy testing data making it feasible to transfer learnt weights in software to a hardware device interfacing with noisy spiking sensors. The new rule improves testing accuracy by 7 - 10% compared to earlier versions. We also present preliminary results for multi-class classification on handwritten digits from the MNIST database and show that our system can attain comparable performance (≈ 3% more error) with other reported spike based classifiers while using at least 50% less synaptic resources. © 2014 IEEE.
UR - https://www.scopus.com/pages/publications/84907384663
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84907384663&origin=recordpage
U2 - 10.1109/ISCAS.2014.6865715
DO - 10.1109/ISCAS.2014.6865715
M3 - RGC 32 - Refereed conference paper (with host publication)
SN - 9781479934324
T3 - Proceedings - IEEE International Symposium on Circuits and Systems
SP - 2640
EP - 2643
BT - 2014 IEEE International Symposium on Circuits and Systems, ISCAS 2014
PB - IEEE
T2 - 2014 IEEE International Symposium on Circuits and Systems, ISCAS 2014
Y2 - 1 June 2014 through 5 June 2014
ER -