Recognition Networks for Approximate Inference in BN20 Networks

By Quaid D. Morris. 2001

27 citations recorded by the source corpus.

A recognition network is a multilayer perception (MLP) trained to predict posterior maxginals given observed evidence in a particulax Bayesian network. The input to the MLP is a vector of the states of the evidential nodes. The activity of an output unit is interpreted as a prediction of the posterior marginal of the corresponding variable. The MLP is trained using samples generated from the corresponding Bayesian network. We evaluate a recognition network that was trained to do inference in a large Bayesian network, similax in structure and complexity to the Quick Medical Reference, Decision Theoretic (QMR-DT) network. Our network is a binary, two-layer, noisy-OR (BN20) network containing over 4000 potentially observable nodes and over 600 unobservable, hidden nodes. In real medical diagnosis, most observables are unavailable, and there is a complex and unknown process that selects which ones axe provided. We incorporate a very basic type of selection bias in our network: a known preference that available observables are positive rather than negative. Even this simple bias has a significant effect on the posterior. We compare the performance of our recognition network to state-of-the-art approximate inference algorithms on a large set of test cases. In order to evaluate the effect of our simplistic model of the selection bias, we evaluate algorithms using a variety of incorrectly modelled selection biases. Recognition networks perform well using both correct and incorrect selection biases.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Improving the accuracy of medical diagnosis with causal machine learning (2020, methodology): “BN disease models have a long history going back to the INTERNIST-1 18 , Quick Medical Reference (QMR) 19,20 , and PATHFINDER 21,22 systems, with many of the original systems corresponding to noisy-OR networks with only disease and symptom nodes, known as BN2O networks 36 .”
MultiVerse: Causal Reasoning using Importance Sampling in Probabilistic Programming (2019, methodology): “…for amortised approximate inference (Gu et al., 2015; Germain et al., 2015; Perov et al., 2015; Paige and Wood, 2016a; Perov, 2016; Le et al., 2016; Morris, 2001; Paige and Wood, 2016b; Ritchie et al., 2016; Le et al., 2017) and in particular importance sampling inference (Douglas et al., 2017;…”
Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flows (2018, methodology): “Beyond SNPE, conditional neural density estimators have been used to learn the posterior from simulations in graphical models [53, 58], and universal probabilistic programs [38].”
Learning Stochastic Inverses (2013, methodology): “A recognition network (Morris, 2001) is a multilayer perceptron used to predict posterior marginals.”
A Universal Marginalizer for Amortized Inference in Generative Models (2017, methodology): “Amortized inference has been popular for Sequential Monte Carlo and has been used to learn in advance either parameters [Gu et al., 2015] or a discriminative model which provides conditional density estimates [Morris, 2001, Paige and Wood, 2016].”
Fast $\epsilon$-free Inference of Simulation Models with Bayesian Conditional Density Estimation (2016, methodology): “Feedforward neural networks have been used to invert black-box generative models [18] and binary-valued Bayesian networks [17], and convolutional neural networks have been used to invert a physics engine [25].”