build based on 3766b6f

dev/.documenter-siteinfo.json

@@ -1 +1 @@
-{"documenter":{"julia_version":"1.9.4","generation_timestamp":"2023-12-19T01:01:18","documenter_version":"1.2.1"}}
+{"documenter":{"julia_version":"1.9.4","generation_timestamp":"2023-12-23T15:08:21","documenter_version":"1.2.1"}}

dev/api/esn/index.html

@@ -3,7 +3,7 @@
 
 train_data = rand(10, 100)  # 10 features, 100 time steps
 
-esn = ESN(train_data, reservoir=RandSparseReservoir(200), washout=10)</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/SciML/ReservoirComputing.jl/blob/ba0c0d5306aa3fb3228fb008fcce9e0c604a6073/src/esn/echostatenetwork.jl#L64-L92">source</a></section></article><h2 id="Variations"><a class="docs-heading-anchor" href="#Variations">Variations</a><a id="Variations-1"></a><a class="docs-heading-anchor-permalink" href="#Variations" title="Permalink"></a></h2><p>In addition to the standard <code>ESN</code> model, there are variations that allow for deeper customization of the underlying model. Currently, there are two available variations: <code>Default</code> and <code>Hybrid</code>. These variations provide different ways to configure the ESN. Here&#39;s the documentation for the variations:</p><article class="docstring"><header><a class="docstring-article-toggle-button fa-solid fa-chevron-down" href="javascript:;" title="Collapse docstring"></a><a class="docstring-binding" id="ReservoirComputing.Default" href="#ReservoirComputing.Default"><code>ReservoirComputing.Default</code></a> — <span class="docstring-category">Type</span></header><section><div><pre><code class="language-julia hljs">Default()</code></pre><p>The <code>Default</code> struct specifies the use of the standard model in Echo State Networks (ESNs). It requires no parameters and is used when no specific variations or customizations of the ESN model are needed. This struct is ideal for straightforward applications where the default ESN settings are sufficient.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/SciML/ReservoirComputing.jl/blob/ba0c0d5306aa3fb3228fb008fcce9e0c604a6073/src/esn/echostatenetwork.jl#L16-L22">source</a></section></article><article class="docstring"><header><a class="docstring-article-toggle-button fa-solid fa-chevron-down" href="javascript:;" title="Collapse docstring"></a><a class="docstring-binding" id="ReservoirComputing.Hybrid" href="#ReservoirComputing.Hybrid"><code>ReservoirComputing.Hybrid</code></a> — <span class="docstring-category">Type</span></header><section><div><pre><code class="language-julia hljs">Hybrid(prior_model, u0, tspan, datasize)</code></pre><p>Constructs a <code>Hybrid</code> variation of Echo State Networks (ESNs) integrating a knowledge-based model (<code>prior_model</code>) with ESNs for advanced training and prediction in chaotic systems. </p><p><strong>Parameters</strong></p><ul><li><code>prior_model</code>: A knowledge-based model function for integration with ESNs.</li><li><code>u0</code>: Initial conditions for the model.</li><li><code>tspan</code>: Time span as a tuple, indicating the duration for model operation.</li><li><code>datasize</code>: The size of the data to be processed.</li></ul><p><strong>Returns</strong></p><ul><li>A <code>Hybrid</code> struct instance representing the combined ESN and knowledge-based model.</li></ul><p>This method is effective for chaotic processes as highlighted in <sup class="footnote-reference"><a id="citeref-Pathak" href="#footnote-Pathak">[Pathak]</a></sup>.</p><p>Reference: <sup class="footnote-reference"><a id="citeref-Pathak" href="#footnote-Pathak">[Pathak]</a></sup>: Jaideep Pathak et al.     &quot;Hybrid Forecasting of Chaotic Processes:     Using Machine Learning in Conjunction with a Knowledge-Based Model&quot; (2018).</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/SciML/ReservoirComputing.jl/blob/ba0c0d5306aa3fb3228fb008fcce9e0c604a6073/src/esn/echostatenetwork.jl#L33-L54">source</a></section></article><p>The <code>Hybrid</code> variation is the most complex option and offers additional customization. Note that more variations may be added in the future to provide even greater flexibility.</p><h2 id="Training"><a class="docs-heading-anchor" href="#Training">Training</a><a id="Training-1"></a><a class="docs-heading-anchor-permalink" href="#Training" title="Permalink"></a></h2><p>To train an ESN model, you can use the <code>train</code> function. It takes the ESN model, training data, and other optional parameters as input and returns a trained model. Here&#39;s the documentation for the train function:</p><article class="docstring"><header><a class="docstring-article-toggle-button fa-solid fa-chevron-down" href="javascript:;" title="Collapse docstring"></a><a class="docstring-binding" id="ReservoirComputing.train" href="#ReservoirComputing.train"><code>ReservoirComputing.train</code></a> — <span class="docstring-category">Function</span></header><section><div><pre><code class="language-julia hljs">train(esn::AbstractEchoStateNetwork, target_data, training_method = StandardRidge(0.0))</code></pre><p>Trains an Echo State Network (ESN) using the provided target data and a specified training method.</p><p><strong>Parameters</strong></p><ul><li><code>esn::AbstractEchoStateNetwork</code>: The ESN instance to be trained.</li><li><code>target_data</code>: Supervised training data for the ESN.</li><li><code>training_method</code>: The method for training the ESN (default: <code>StandardRidge(0.0)</code>).</li></ul><p><strong>Returns</strong></p><ul><li>The trained ESN model. Its type and structure depend on <code>training_method</code> and the ESN&#39;s implementation.</li></ul><p><strong>Returns</strong></p><p>The trained ESN model. The exact type and structure of the return value depends on the <code>training_method</code> and the specific ESN implementation.</p><pre><code class="language-julia hljs">using ReservoirComputing
+esn = ESN(train_data, reservoir=RandSparseReservoir(200), washout=10)</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/SciML/ReservoirComputing.jl/blob/3766b6f9be40cbbf4695423b7c3c093e526f64eb/src/esn/echostatenetwork.jl#L64-L92">source</a></section></article><h2 id="Variations"><a class="docs-heading-anchor" href="#Variations">Variations</a><a id="Variations-1"></a><a class="docs-heading-anchor-permalink" href="#Variations" title="Permalink"></a></h2><p>In addition to the standard <code>ESN</code> model, there are variations that allow for deeper customization of the underlying model. Currently, there are two available variations: <code>Default</code> and <code>Hybrid</code>. These variations provide different ways to configure the ESN. Here&#39;s the documentation for the variations:</p><article class="docstring"><header><a class="docstring-article-toggle-button fa-solid fa-chevron-down" href="javascript:;" title="Collapse docstring"></a><a class="docstring-binding" id="ReservoirComputing.Default" href="#ReservoirComputing.Default"><code>ReservoirComputing.Default</code></a> — <span class="docstring-category">Type</span></header><section><div><pre><code class="language-julia hljs">Default()</code></pre><p>The <code>Default</code> struct specifies the use of the standard model in Echo State Networks (ESNs). It requires no parameters and is used when no specific variations or customizations of the ESN model are needed. This struct is ideal for straightforward applications where the default ESN settings are sufficient.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/SciML/ReservoirComputing.jl/blob/3766b6f9be40cbbf4695423b7c3c093e526f64eb/src/esn/echostatenetwork.jl#L16-L22">source</a></section></article><article class="docstring"><header><a class="docstring-article-toggle-button fa-solid fa-chevron-down" href="javascript:;" title="Collapse docstring"></a><a class="docstring-binding" id="ReservoirComputing.Hybrid" href="#ReservoirComputing.Hybrid"><code>ReservoirComputing.Hybrid</code></a> — <span class="docstring-category">Type</span></header><section><div><pre><code class="language-julia hljs">Hybrid(prior_model, u0, tspan, datasize)</code></pre><p>Constructs a <code>Hybrid</code> variation of Echo State Networks (ESNs) integrating a knowledge-based model (<code>prior_model</code>) with ESNs for advanced training and prediction in chaotic systems. </p><p><strong>Parameters</strong></p><ul><li><code>prior_model</code>: A knowledge-based model function for integration with ESNs.</li><li><code>u0</code>: Initial conditions for the model.</li><li><code>tspan</code>: Time span as a tuple, indicating the duration for model operation.</li><li><code>datasize</code>: The size of the data to be processed.</li></ul><p><strong>Returns</strong></p><ul><li>A <code>Hybrid</code> struct instance representing the combined ESN and knowledge-based model.</li></ul><p>This method is effective for chaotic processes as highlighted in <sup class="footnote-reference"><a id="citeref-Pathak" href="#footnote-Pathak">[Pathak]</a></sup>.</p><p>Reference: <sup class="footnote-reference"><a id="citeref-Pathak" href="#footnote-Pathak">[Pathak]</a></sup>: Jaideep Pathak et al.     &quot;Hybrid Forecasting of Chaotic Processes:     Using Machine Learning in Conjunction with a Knowledge-Based Model&quot; (2018).</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/SciML/ReservoirComputing.jl/blob/3766b6f9be40cbbf4695423b7c3c093e526f64eb/src/esn/echostatenetwork.jl#L33-L54">source</a></section></article><p>The <code>Hybrid</code> variation is the most complex option and offers additional customization. Note that more variations may be added in the future to provide even greater flexibility.</p><h2 id="Training"><a class="docs-heading-anchor" href="#Training">Training</a><a id="Training-1"></a><a class="docs-heading-anchor-permalink" href="#Training" title="Permalink"></a></h2><p>To train an ESN model, you can use the <code>train</code> function. It takes the ESN model, training data, and other optional parameters as input and returns a trained model. Here&#39;s the documentation for the train function:</p><article class="docstring"><header><a class="docstring-article-toggle-button fa-solid fa-chevron-down" href="javascript:;" title="Collapse docstring"></a><a class="docstring-binding" id="ReservoirComputing.train" href="#ReservoirComputing.train"><code>ReservoirComputing.train</code></a> — <span class="docstring-category">Function</span></header><section><div><pre><code class="language-julia hljs">train(esn::AbstractEchoStateNetwork, target_data, training_method = StandardRidge(0.0))</code></pre><p>Trains an Echo State Network (ESN) using the provided target data and a specified training method.</p><p><strong>Parameters</strong></p><ul><li><code>esn::AbstractEchoStateNetwork</code>: The ESN instance to be trained.</li><li><code>target_data</code>: Supervised training data for the ESN.</li><li><code>training_method</code>: The method for training the ESN (default: <code>StandardRidge(0.0)</code>).</li></ul><p><strong>Returns</strong></p><ul><li>The trained ESN model. Its type and structure depend on <code>training_method</code> and the ESN&#39;s implementation.</li></ul><p><strong>Returns</strong></p><p>The trained ESN model. The exact type and structure of the return value depends on the <code>training_method</code> and the specific ESN implementation.</p><pre><code class="language-julia hljs">using ReservoirComputing
 
 # Initialize an ESN instance and target data
 esn = ESN(train_data, reservoir=RandSparseReservoir(200), washout=10)
@@ -13,4 +13,4 @@
 trained_esn = train(esn, target_data)
 
 # Train the ESN using a custom training method
-trained_esn = train(esn, target_data, training_method=StandardRidge(1.0))</code></pre><p><strong>Notes</strong></p><ul><li>When using a <code>Hybrid</code> variation, the function extends the state matrix with data from the   physical model included in the <code>variation</code>.</li><li>The training is handled by a lower-level <code>_train</code> function which takes the new state matrix   and performs the actual training using the specified <code>training_method</code>.</li></ul></div><a class="docs-sourcelink" target="_blank" href="https://github.com/SciML/ReservoirComputing.jl/blob/ba0c0d5306aa3fb3228fb008fcce9e0c604a6073/src/esn/echostatenetwork.jl#L209-L246">source</a></section></article><p>With these components and variations, you can configure and train ESN models for various time series and sequential data prediction tasks.</p></article><nav class="docs-footer"><a class="docs-footer-prevpage" href="../predict/">« Prediction Types</a><a class="docs-footer-nextpage" href="../esn_layers/">ESN Layers »</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="documenter-light">documenter-light</option><option value="documenter-dark">documenter-dark</option><option value="auto">Automatic (OS)</option></select></div></p><hr/><p>This document was generated with <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> version 1.2.1 on <span class="colophon-date" title="Tuesday 19 December 2023 01:01">Tuesday 19 December 2023</span>. Using Julia version 1.9.4.</p></section><footer class="modal-card-foot"></footer></div></div></div></body></html>
+trained_esn = train(esn, target_data, training_method=StandardRidge(1.0))</code></pre><p><strong>Notes</strong></p><ul><li>When using a <code>Hybrid</code> variation, the function extends the state matrix with data from the   physical model included in the <code>variation</code>.</li><li>The training is handled by a lower-level <code>_train</code> function which takes the new state matrix   and performs the actual training using the specified <code>training_method</code>.</li></ul></div><a class="docs-sourcelink" target="_blank" href="https://github.com/SciML/ReservoirComputing.jl/blob/3766b6f9be40cbbf4695423b7c3c093e526f64eb/src/esn/echostatenetwork.jl#L209-L246">source</a></section></article><p>With these components and variations, you can configure and train ESN models for various time series and sequential data prediction tasks.</p></article><nav class="docs-footer"><a class="docs-footer-prevpage" href="../predict/">« Prediction Types</a><a class="docs-footer-nextpage" href="../esn_layers/">ESN Layers »</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="documenter-light">documenter-light</option><option value="documenter-dark">documenter-dark</option><option value="auto">Automatic (OS)</option></select></div></p><hr/><p>This document was generated with <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> version 1.2.1 on <span class="colophon-date" title="Saturday 23 December 2023 15:08">Saturday 23 December 2023</span>. Using Julia version 1.9.4.</p></section><footer class="modal-card-foot"></footer></div></div></div></body></html>