Training Dynamic Exponential Family Models with Causal and Lateral Dependencies for Generalized Neuromorphic Computing
This work addresses the need for more flexible models in neuromorphic computing, but it is incremental as it builds on existing exponential family harmoniums.
The paper tackled the problem of modeling generalized neuromorphic computing systems with arbitrary synaptic alphabets and dependencies by introducing a probabilistic model as an extension of exponential family harmoniums to time series, and derived distributed learning rules for Maximum Likelihood and Bayesian criteria.
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.