📄 reference.html.svn-base
字号:
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd"><html><head> <meta name="resource-type" content="document"> <meta http-equiv="pragma" content="no-cache"> <meta name="revisit-after" content="10"> <meta name="classification" content="Jean-No毛l Rivasseau"> <meta name="description" content="This is the personal homepage of Jean-No毛l Rivasseau, listing professional and personal projects and interests."> <meta name="keywords" content="jean-no毛l, jean-noel, rivasseau, jean, noel, no毛l, machine-learning, machine, learning, music, UBC, vancouver, computer, science, graduate, student, polytechnique, linux, powerpc, ppc, composition, research, russia, tchastouchki, mac, games, hiking, canada, france, role-playing, board, mac os x, university, british, columbia, open source, statistical inference, markov chains, mcmc, monte carlo, artificial intelligence, inference algorithms, belief propagation, bayesian networks, gibbs, gibbs sampler, markov random fields, mcmc, smc, particle filters, bayesian filtering"> <meta name="distribution" content="Global"> <meta name="rating" content="General"> <meta name="copyright" content="Copyright 2003-2007, Jean-No毛l Rivasseau. All rights reserved."> <meta name="author" content="Jean-No毛l Rivasseau"> <meta name="language" content="English"> <meta name="doc-type" content="Web Page"> <meta name="doc-class" content="Living Document"> <meta name="doc-rights" content="Copywritten Work"> <title>PGM Reference</title><meta http-equiv="Content-Type" content="text/html; charset=utf-8"></head><body><h1>Reference for pgm input file format</h1><p>This documents the input format used by PGM to compute inference. The work of the Matlab M-files is to generate a file in this format.</p><hr><p style="font-weight: bold;"><method></p><ul><li> <span style="font-weight: bold;">(tree_partition)</span></li><p style="padding-left: 40pt;">This does not perform inference, but only computes a tree partition.</p><li> <span style="font-weight: bold;">(tree_mcmc) (number_steps)</span></li><p style="padding-left: 40pt;">This perform inference using Tree Sampling with Rao-Blackwellization, with the given number of steps.</p><li> <span style="font-weight: bold;">(tree_mcmc_no_rb) (number_steps)</span></li><p style="padding-left: 40pt;">This perform inference using Tree Sampling WITHOUT Rao-Blackwellization, with the given number of steps.</p></ul><p style="font-weight: bold;"><all potential tables></p><ul><li> <span style="font-weight: bold;">(all-random)</span></li><p style="padding-left: 40pt;">This will create all the potentials at random, and the potentials will all be different from each other.</p><li> <span style="font-weight: bold;">(all-random-strongly-diagonal-uniform-noise) (a)</span></li><p style="padding-left: 40pt;">This will create an unique potential table, used for all potentials, with uniform noise and strongly diagonal coefficients. <span style="font-weight: bold;">a</span> will be used as the strongly diagonal coefficient.</p></ul><hr><p style="font-weight: bold;"><timer></p><p style="padding-left: 40pt;">This instructs the inference engine to use a timer; e.g., the computational time will be measured with real seconds instead of steps.</p><p style="font-weight: bold;"><monitor></p><p style="padding-left: 40pt;">This activates monitoring, allowing errors to be computed at each step/second.</p><p style="font-weight: bold;"><number of runs> (a)</p><p style="padding-left: 40pt;">This will make the requested number of runs (specified by <span style="font-weight: bold;">a</span>), instead of a single run.</p><p style="font-weight: bold;"><observations> (a b) ... (a b)</p><p style="padding-left: 40pt;">The variables represented by the indexes <span style="font-weight: bold;">a</span> will be set observed to the values <span style="font-weight: bold;">b</span>.</p><p style="font-weight: bold;"><internal potentials> (a) ( x ... z ) ... (a) ( x ... z ) </p><p style="padding-left: 40pt;">The variables represented by the indexes <span style="font-weight: bold;">a</span> will get their priors (internal potentials) set to the vector given by values <span style="font-weight: bold;">x ... z</span>.</p></body></html>⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -