Linear-Nonlinear-Poisson Neuron Networks Perform Bayesian Inference On Boltzmann Machines
نویسنده
چکیده
One conjecture in both deep learning and classical connectionist viewpoint is that the biological brain implements certain kinds of deep networks as its backend. However, to our knowledge, a detailed correspondence has not yet been set up, which is important if we want to bridge between neuroscience and machine learning. Recent researches emphasized the biological plausibility of LinearNonlinear-Poisson (LNP) neuron model. We show that with neurally plausible settings, the whole network is capable of representing any Boltzmann machine and performing a semi-stochastic Bayesian inference algorithm lying between Gibbs sampling and variational inference.
منابع مشابه
Linear-Nonlinear-Poisson Neurons Can Do Inference On Deep Boltzmann Machines
One conjecture in both deep learning and classical connectionist viewpoint is that the biological brain implements certain kinds of deep networks as its backend. However, to our knowledge, a detailed correspondence has not yet been set up, which is important if we want to bridge between neuroscience and machine learning. Recent researches emphasized the biological plausibility of LinearNonlinea...
متن کاملModeling environmental indicators for land leveling, using Artificial Neural Networks and Adaptive Neuron-Fuzzy Inference System
Land leveling is one of the most important steps in soil preparation and cultivation. Although land leveling with machines requires considerable amount of energy, it delivers a suitable surface slope with minimal soil deterioration as well as damage to plants and other organisms in the soil. Notwithstanding, in recent years researchers have tried to reduce fossil fuel consumption and its delete...
متن کاملModeling environmental indicators for land leveling, using Artificial Neural Networks and Adaptive Neuron-Fuzzy Inference System
Land leveling is one of the most important steps in soil preparation and cultivation. Although land leveling with machines requires considerable amount of energy, it delivers a suitable surface slope with minimal soil deterioration as well as damage to plants and other organisms in the soil. Notwithstanding, in recent years researchers have tried to reduce fossil fuel consumption and its delete...
متن کاملFunctional Distributional Semantics
Vector space models have become popular in distributional semantics, despite the challenges they face in capturing various semantic phenomena. We propose a novel probabilistic framework which draws on both formal semantics and recent advances in machine learning. In particular, we separate predicates from the entities they refer to, allowing us to perform Bayesian inference based on logical for...
متن کاملModeling Nonlinear Deterministic Relationships in Bayesian Networks
In a Bayesian network with continuous variables containing a variable(s) that is a conditionally deterministic function of its continuous parents, the joint density function for the variables in the network does not exist. Conditional linear Gaussian distributions can handle such cases when the deterministic function is linear and the continuous variables have a multi-variate normal distributio...
متن کامل