Learning and relearning in Boltzmann machines
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Continuous-valued probabilistic behavior in a VLSI generative model
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
Implementing probabilistic models in the Very-Large-Scale- Integration (VLSI) has been attractive to implantable biomedical devices for improving sensor fusion and power management. However, implantable devices are normally exposed to noisy environments which can introduce non-negligible computational errors and hinder optimal modelling on-chip. While the probablistic model called the Continuous Restricted Boltzmann Machine (CRBM) has been shown useful and realised as a VLSI system with noise-induced stochastic behaviour, this paper investigates the suggestion that the stochastic behaviour in VLSI could enhance the tolerance against the interferences of environmental noise. The behavioural simulation of the CRBM system is used to examine the system's performance in the presence of environmental noise. Furthermore, the possibility of using environmental noise to induce stochasticity in VLSI for computation is investigated.