Skip to content

Commit

Permalink
build based on 583e48f
Browse files Browse the repository at this point in the history
  • Loading branch information
Documenter.jl committed Apr 5, 2024
1 parent 8fff39f commit 48dae29
Show file tree
Hide file tree
Showing 26 changed files with 1,844 additions and 3 deletions.
2 changes: 1 addition & 1 deletion stable
View file
Original file line number Diff line number Diff line change
@@ -1 +1 @@
v0.5.0
v0.5.1
2 changes: 1 addition & 1 deletion v0.5
View file
Original file line number Diff line number Diff line change
@@ -1 +1 @@
v0.5.0
v0.5.1
1 change: 1 addition & 0 deletions v0.5.1/.documenter-siteinfo.json
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"documenter":{"julia_version":"1.10.2","generation_timestamp":"2024-04-05T10:57:54","documenter_version":"1.3.0"}}
2 changes: 2 additions & 0 deletions v0.5.1/alternatives/index.html
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
<!DOCTYPE html>
<html lang="en"><head><meta charset="UTF-8"/><meta name="viewport" content="width=device-width, initial-scale=1.0"/><title>Alternatives · HiddenMarkovModels.jl</title><meta name="title" content="Alternatives · HiddenMarkovModels.jl"/><meta property="og:title" content="Alternatives · HiddenMarkovModels.jl"/><meta property="twitter:title" content="Alternatives · HiddenMarkovModels.jl"/><meta name="description" content="Documentation for HiddenMarkovModels.jl."/><meta property="og:description" content="Documentation for HiddenMarkovModels.jl."/><meta property="twitter:description" content="Documentation for HiddenMarkovModels.jl."/><meta property="og:url" content="https://gdalle.github.io/HiddenMarkovModels.jl/alternatives/"/><meta property="twitter:url" content="https://gdalle.github.io/HiddenMarkovModels.jl/alternatives/"/><link rel="canonical" href="https://gdalle.github.io/HiddenMarkovModels.jl/alternatives/"/><script data-outdated-warner src="../assets/warner.js"></script><link href="https://cdnjs.cloudflare.com/ajax/libs/lato-font/3.0.0/css/lato-font.min.css" rel="stylesheet" type="text/css"/><link href="https://cdnjs.cloudflare.com/ajax/libs/juliamono/0.050/juliamono.min.css" rel="stylesheet" type="text/css"/><link href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.2/css/fontawesome.min.css" rel="stylesheet" type="text/css"/><link href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.2/css/solid.min.css" rel="stylesheet" type="text/css"/><link href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.2/css/brands.min.css" rel="stylesheet" type="text/css"/><link href="https://cdnjs.cloudflare.com/ajax/libs/KaTeX/0.16.8/katex.min.css" rel="stylesheet" type="text/css"/><script>documenterBaseURL=".."</script><script src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.6/require.min.js" data-main="../assets/documenter.js"></script><script src="../search_index.js"></script><script src="../siteinfo.js"></script><script src="../../versions.js"></script><link class="docs-theme-link" rel="stylesheet" type="text/css" href="../assets/themes/documenter-dark.css" data-theme-name="documenter-dark" data-theme-primary-dark/><link class="docs-theme-link" rel="stylesheet" type="text/css" href="../assets/themes/documenter-light.css" data-theme-name="documenter-light" data-theme-primary/><script src="../assets/themeswap.js"></script></head><body><div id="documenter"><nav class="docs-sidebar"><a class="docs-logo" href="../"><img src="../assets/logo.png" alt="HiddenMarkovModels.jl logo"/></a><div class="docs-package-name"><span class="docs-autofit"><a href="../">HiddenMarkovModels.jl</a></span></div><button class="docs-search-query input is-rounded is-small is-clickable my-2 mx-auto py-1 px-2" id="documenter-search-query">Search docs (Ctrl + /)</button><ul class="docs-menu"><li><a class="tocitem" href="../">Home</a></li><li><span class="tocitem">Tutorials</span><ul><li><a class="tocitem" href="../examples/basics/">Basics</a></li><li><a class="tocitem" href="../examples/types/">Types</a></li><li><a class="tocitem" href="../examples/interfaces/">Interfaces</a></li><li><a class="tocitem" href="../examples/temporal/">Time dependency</a></li><li><a class="tocitem" href="../examples/controlled/">Control dependency</a></li><li><a class="tocitem" href="../examples/autodiff/">Autodiff</a></li></ul></li><li><a class="tocitem" href="../api/">API reference</a></li><li><span class="tocitem">Advanced</span><ul><li class="is-active"><a class="tocitem" href>Alternatives</a><ul class="internal"><li><a class="tocitem" href="#Julia"><span>Julia</span></a></li><li><a class="tocitem" href="#Python"><span>Python</span></a></li></ul></li><li><a class="tocitem" href="../debugging/">Debugging</a></li><li><a class="tocitem" href="../formulas/">Formulas</a></li></ul></li></ul><div class="docs-version-selector field has-addons"><div class="control"><span class="docs-label button is-static is-size-7">Version</span></div><div class="docs-selector control is-expanded"><div class="select is-fullwidth is-size-7"><select id="documenter-version-selector"></select></div></div></div></nav><div class="docs-main"><header class="docs-navbar"><a class="docs-sidebar-button docs-navbar-link fa-solid fa-bars is-hidden-desktop" id="documenter-sidebar-button" href="#"></a><nav class="breadcrumb"><ul class="is-hidden-mobile"><li><a class="is-disabled">Advanced</a></li><li class="is-active"><a href>Alternatives</a></li></ul><ul class="is-hidden-tablet"><li class="is-active"><a href>Alternatives</a></li></ul></nav><div class="docs-right"><a class="docs-navbar-link" href="https://github.com/gdalle/HiddenMarkovModels.jl" title="View the repository on GitHub"><span class="docs-icon fa-brands"></span><span class="docs-label is-hidden-touch">GitHub</span></a><a class="docs-navbar-link" href="https://github.com/gdalle/HiddenMarkovModels.jl/blob/main/docs/src/alternatives.md" title="Edit source on GitHub"><span class="docs-icon fa-solid"></span></a><a class="docs-settings-button docs-navbar-link fa-solid fa-gear" id="documenter-settings-button" href="#" title="Settings"></a><a class="docs-article-toggle-button fa-solid fa-chevron-up" id="documenter-article-toggle-button" href="javascript:;" title="Collapse all docstrings"></a></div></header><article class="content" id="documenter-page"><h1 id="Competitors"><a class="docs-heading-anchor" href="#Competitors">Competitors</a><a id="Competitors-1"></a><a class="docs-heading-anchor-permalink" href="#Competitors" title="Permalink"></a></h1><h2 id="Julia"><a class="docs-heading-anchor" href="#Julia">Julia</a><a id="Julia-1"></a><a class="docs-heading-anchor-permalink" href="#Julia" title="Permalink"></a></h2><p>We compare features among the following Julia packages:</p><ul><li>HiddenMarkovModels.jl</li><li><a href="https://github.com/maxmouchet/HMMBase.jl">HMMBase.jl</a></li><li><a href="https://github.com/idiap/HMMGradients.jl">HMMGradients.jl</a></li></ul><p>We discard <a href="https://github.com/FAST-ASR/MarkovModels.jl">MarkovModels.jl</a> because its focus is GPU computation. There are also more generic packages for probabilistic programming, which are able to perform MCMC or variational inference (eg. <a href="https://github.com/TuringLang/Turing.jl">Turing.jl</a>) but we leave those aside.</p><table><tr><th style="text-align: right"></th><th style="text-align: right">HiddenMarkovModels.jl</th><th style="text-align: right">HMMBase.jl</th><th style="text-align: right">HMMGradients.jl</th></tr><tr><td style="text-align: right">Algorithms<sup class="footnote-reference"><a id="citeref-1" href="#footnote-1">[1]</a></sup></td><td style="text-align: right">V, FB, BW</td><td style="text-align: right">V, FB, BW</td><td style="text-align: right">FB</td></tr><tr><td style="text-align: right">Number types</td><td style="text-align: right">anything</td><td style="text-align: right"><code>Float64</code></td><td style="text-align: right"><code>AbstractFloat</code></td></tr><tr><td style="text-align: right">Observation types</td><td style="text-align: right">anything</td><td style="text-align: right">number or vector</td><td style="text-align: right">anything</td></tr><tr><td style="text-align: right">Observation distributions</td><td style="text-align: right">DensityInterface.jl</td><td style="text-align: right">Distributions.jl</td><td style="text-align: right">manual</td></tr><tr><td style="text-align: right">Multiple sequences</td><td style="text-align: right">yes</td><td style="text-align: right">no</td><td style="text-align: right">yes</td></tr><tr><td style="text-align: right">Priors / structures</td><td style="text-align: right">possible</td><td style="text-align: right">no</td><td style="text-align: right">possible</td></tr><tr><td style="text-align: right">Control dependency</td><td style="text-align: right">yes</td><td style="text-align: right">no</td><td style="text-align: right">no</td></tr><tr><td style="text-align: right">Automatic differentiation</td><td style="text-align: right">yes</td><td style="text-align: right">no</td><td style="text-align: right">yes</td></tr><tr><td style="text-align: right">Linear algebra speedup</td><td style="text-align: right">yes</td><td style="text-align: right">yes</td><td style="text-align: right">no</td></tr><tr><td style="text-align: right">Numerical stability</td><td style="text-align: right">scaling+</td><td style="text-align: right">scaling+</td><td style="text-align: right">log</td></tr></table><div class="admonition is-info"><header class="admonition-header">Very small probabilities</header><div class="admonition-body"><p>In all HMM algorithms, we work with probabilities that may become very small as time progresses. There are two main solutions for this problem: scaling and logarithmic computations. This package implements the Viterbi algorithm in log scale, but the other algorithms use scaling to exploit BLAS operations. As was done in HMMBase.jl, we enhance scaling with a division by the highest observation loglikelihood: instead of working with <span>$b_{i,t} = \mathbb{P}(Y_t | X_t = i)$</span>, we use <span>$b_{i,t} / \max_i b_{i,t}$</span>. See <a href="../formulas/#Formulas">Formulas</a> for details.</p></div></div><h2 id="Python"><a class="docs-heading-anchor" href="#Python">Python</a><a id="Python-1"></a><a class="docs-heading-anchor-permalink" href="#Python" title="Permalink"></a></h2><p>We compare features among the following Python packages:</p><ul><li><a href="https://github.com/hmmlearn/hmmlearn">hmmlearn</a> (based on NumPy)</li><li><a href="https://github.com/jmschrei/pomegranate">pomegranate</a> (based on PyTorch)</li><li><a href="https://github.com/probml/dynamax">dynamax</a> (based on JAX)</li></ul><table><tr><th style="text-align: right"></th><th style="text-align: right">hmmlearn</th><th style="text-align: right">pomegranate</th><th style="text-align: right">dynamax</th></tr><tr><td style="text-align: right">Algorithms<sup class="footnote-reference"><a id="citeref-1" href="#footnote-1">[1]</a></sup></td><td style="text-align: right">V, FB, BW, VI</td><td style="text-align: right">FB, BW</td><td style="text-align: right">FB, V, BW, GD</td></tr><tr><td style="text-align: right">Number types</td><td style="text-align: right">NumPy formats</td><td style="text-align: right">PyTorch formats</td><td style="text-align: right">JAX formats</td></tr><tr><td style="text-align: right">Observation types</td><td style="text-align: right">number or vector</td><td style="text-align: right">number or vector</td><td style="text-align: right">number or vector</td></tr><tr><td style="text-align: right">Observation distributions</td><td style="text-align: right">hmmlearn catalogue</td><td style="text-align: right">pomegranate catalogue</td><td style="text-align: right">dynamax catalogue</td></tr><tr><td style="text-align: right">Multiple sequences</td><td style="text-align: right">yes</td><td style="text-align: right">yes</td><td style="text-align: right">yes</td></tr><tr><td style="text-align: right">Priors / structures</td><td style="text-align: right">yes</td><td style="text-align: right">no</td><td style="text-align: right">yes</td></tr><tr><td style="text-align: right">Control dependency</td><td style="text-align: right">no</td><td style="text-align: right">no</td><td style="text-align: right">yes</td></tr><tr><td style="text-align: right">Automatic differentiation</td><td style="text-align: right">no</td><td style="text-align: right">yes</td><td style="text-align: right">yes</td></tr><tr><td style="text-align: right">Linear algebra speedup</td><td style="text-align: right">yes</td><td style="text-align: right">yes</td><td style="text-align: right">yes</td></tr><tr><td style="text-align: right">Numerical stability</td><td style="text-align: right">scaling / log</td><td style="text-align: right">log</td><td style="text-align: right">log</td></tr></table><section class="footnotes is-size-7"><ul><li class="footnote" id="footnote-1"><a class="tag is-link" href="#citeref-1">1</a>V = Viterbi, FB = Forward-Backward, BW = Baum-Welch, VI = Variational Inference, GD = Gradient Descent</li></ul></section></article><nav class="docs-footer"><a class="docs-footer-prevpage" href="../api/">« API reference</a><a class="docs-footer-nextpage" href="../debugging/">Debugging »</a><div class="flexbox-break"></div><p class="footer-message">Powered by <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> and the <a href="https://julialang.org/">Julia Programming Language</a>.</p></nav></div><div class="modal" id="documenter-settings"><div class="modal-background"></div><div class="modal-card"><header class="modal-card-head"><p class="modal-card-title">Settings</p><button class="delete"></button></header><section class="modal-card-body"><p><label class="label">Theme</label><div class="select"><select id="documenter-themepicker"><option value="auto">Automatic (OS)</option><option value="documenter-light">documenter-light</option><option value="documenter-dark">documenter-dark</option></select></div></p><hr/><p>This document was generated with <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> version 1.3.0 on <span class="colophon-date" title="Friday 5 April 2024 10:57">Friday 5 April 2024</span>. Using Julia version 1.10.2.</p></section><footer class="modal-card-foot"></footer></div></div></div></body></html>
Loading

0 comments on commit 48dae29

Please sign in to comment.