Stochastic variability is present across all scales of brain activity. At the single-cell level, for instance, synaptic transmission is mediated by stochastic release of neurotransmitter and membrane potentials fluctuate due to random conformational changes of ion channels. When these cell-level sources of stochastic variability emerge at the network level, they generate fluctuating currents th...

A method is provided for designing and training noise-driven recurrent neural networks as models of stochastic processes. The method unifies and generalizes two known separate modeling approaches, Echo State Networks (ESN) and Linear Inverse Modeling (LIM), under the common principle of relative entropy minimization. The power of the new method is demonstrated on a stochastic approximation of t...

This article considers the stochastic modeling of vehicular network flows, including the analytical approximation of joint queue-length distributions. The article presents two main methodological contributions. First, it proposes a tractable network model for finite space capacity Markovian queueing networks. This methodology decomposes a general topology queueing network into a set of overlapp...

This paper presents a new stochastic learning approach to construct a latent variable model for recurrent neural network (RNN) based speech recognition. A hybrid generative and discriminative stochastic network is implemented to build a deep classification model. In the implementation, we conduct stochastic modeling for hidden states of recurrent neural network based on the variational auto-enc...

Loss is an important parameter of Quality of Service (QoS). Though stochastic network calculus is a very useful tool for performance evaluation of computer networks, existing studies on stochastic service guarantees mainly focused on the delay and backlog. Some efforts have been made to analyse loss by deterministic network calculus, but there are few results to extend stochastic network calcul...