[ci skip] MTN Added model state to the glossary (#857) 8b79bc0

Author: ArturoAmorQ

_sources/appendix/glossary.md

@@ -210,6 +210,14 @@ In scikit-learn jargon: an [estimator](#estimator) that takes another
 Generic term that refers to something that can [learn](#train-learn-fit)
 [prediction](#predict-prediction) rules from the data.
 
+### model state
+
+Set of numerical values that an [estimator](#estimator) learns during training.
+They summarize patterns in the data (limited to what the [estimator](#estimator)
+can represent), and are stored for later predictions or transformations.
+Examples include the slope and intercept in a linear regression; or the
+per-feature mean and standard deviation in a standard scaler.
+
 ### overfitting
 
 Overfitting occurs when your [model](#model) stick too closely to the [training
@@ -357,8 +365,8 @@ In a more abstract manner, we can represent fitting with the following diagram:
 
 ![img](https://inria.github.io/scikit-learn-mooc/_images/api_diagram-predictor.fit.svg)
 
-The model state are indeed the parameters and the jockey wheels are referring to
-an optimization algorithm to find the best parameters.
+The [model state](#model-state) are indeed the parameters and the jockey wheels
+are referring to an optimization algorithm to find the best parameters.
 
 ### train set
 

appendix/glossary.html

@@ -677,6 +677,7 @@ <h2> Contents </h2>
 <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#learned-parameters">learned parameters</a></li>
 <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#meta-estimator">meta-estimator</a></li>
 <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#model">model</a></li>
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#model-state">model state</a></li>
 <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#overfitting">overfitting</a></li>
 <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#predictor">predictor</a></li>
 <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#predict-prediction">predict, prediction</a></li>
@@ -902,6 +903,14 @@ <h3>model<a class="headerlink" href="#model" title="Link to this heading">#</a><
 <p>Generic term that refers to something that can <a class="reference internal" href="#train-learn-fit"><span class="xref myst">learn</span></a>
 <a class="reference internal" href="#predict-prediction"><span class="xref myst">prediction</span></a> rules from the data.</p>
 </section>
+<section id="model-state">
+<h3>model state<a class="headerlink" href="#model-state" title="Link to this heading">#</a></h3>
+<p>Set of numerical values that an <a class="reference internal" href="#estimator"><span class="xref myst">estimator</span></a> learns during training.
+They summarize patterns in the data (limited to what the <a class="reference internal" href="#estimator"><span class="xref myst">estimator</span></a>
+can represent), and are stored for later predictions or transformations.
+Examples include the slope and intercept in a linear regression; or the
+per-feature mean and standard deviation in a standard scaler.</p>
+</section>
 <section id="overfitting">
 <h3>overfitting<a class="headerlink" href="#overfitting" title="Link to this heading">#</a></h3>
 <p>Overfitting occurs when your <a class="reference internal" href="#model"><span class="xref myst">model</span></a> stick too closely to the <a class="reference internal" href="#train-set"><span class="xref myst">training
@@ -1029,8 +1038,8 @@ <h3>train, learn, fit<a class="headerlink" href="#train-learn-fit" title="Link t
 possible parameters <code class="docutils literal notranslate"><span class="pre">a</span></code> and <code class="docutils literal notranslate"><span class="pre">b</span></code> fulfilling this requirement.</p>
 <p>In a more abstract manner, we can represent fitting with the following diagram:</p>
 <p><img alt="img" src="https://inria.github.io/scikit-learn-mooc/_images/api_diagram-predictor.fit.svg" /></p>
-<p>The model state are indeed the parameters and the jockey wheels are referring to
-an optimization algorithm to find the best parameters.</p>
+<p>The <a class="reference internal" href="#model-state"><span class="xref myst">model state</span></a> are indeed the parameters and the jockey wheels
+are referring to an optimization algorithm to find the best parameters.</p>
 </section>
 <section id="train-set">
 <h3>train set<a class="headerlink" href="#train-set" title="Link to this heading">#</a></h3>
@@ -1180,6 +1189,7 @@ <h2>Other useful glossaries<a class="headerlink" href="#other-useful-glossaries"
 <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#learned-parameters">learned parameters</a></li>
 <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#meta-estimator">meta-estimator</a></li>
 <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#model">model</a></li>
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#model-state">model state</a></li>
 <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#overfitting">overfitting</a></li>
 <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#predictor">predictor</a></li>
 <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#predict-prediction">predict, prediction</a></li>