TY - GEN
T1 - Training Dynamic Exponential Family Models with Causal and Lateral Dependencies for Generalized Neuromorphic Computing
AU - Jang, Hyeryung
AU - Simeone, Osvaldo
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/5
Y1 - 2019/5
N2 - Neuromorphic hardware platforms, such as Intel's Loihi chip, support the implementation of Spiking Neural Networks (SNNs) as an energy-efficient alternative to Artificial Neural Networks (ANNs). SNNs are networks of neurons with internal analogue dynamics that communicate by means of binary time series. In this work, a probabilistic model is introduced for a generalized set-up in which the synaptic time series can take values in an arbitrary alphabet and are characterized by both causal and instantaneous statistical dependencies. The model, which can be considered as an extension of exponential family harmoniums to time series, is introduced by means of a hybrid directed-undirected graphical representation. Furthermore, distributed learning rules are derived for Maximum Likelihood and Bayesian criteria under the assumption of fully observed time series in the training set.
AB - Neuromorphic hardware platforms, such as Intel's Loihi chip, support the implementation of Spiking Neural Networks (SNNs) as an energy-efficient alternative to Artificial Neural Networks (ANNs). SNNs are networks of neurons with internal analogue dynamics that communicate by means of binary time series. In this work, a probabilistic model is introduced for a generalized set-up in which the synaptic time series can take values in an arbitrary alphabet and are characterized by both causal and instantaneous statistical dependencies. The model, which can be considered as an extension of exponential family harmoniums to time series, is introduced by means of a hybrid directed-undirected graphical representation. Furthermore, distributed learning rules are derived for Maximum Likelihood and Bayesian criteria under the assumption of fully observed time series in the training set.
KW - Bayesian learning
KW - Maximum Likelihood
KW - Spiking Neural Network (SNN)
KW - exponential family model
KW - neuromorphic computing
UR - http://www.scopus.com/inward/record.url?scp=85069004106&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85069004106&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2019.8682960
DO - 10.1109/ICASSP.2019.8682960
M3 - Conference contribution
AN - SCOPUS:85069004106
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 3382
EP - 3386
BT - 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
Y2 - 12 May 2019 through 17 May 2019
ER -