| <!DOCTYPE html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><meta name="generator" content="rustdoc"><meta name="description" content="Source of the Rust file `/root/.cargo/git/checkouts/incubator-teaclave-crates-c8106113f74feefc/ede1f68/rusty-machine/src/learning/nnet/mod.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>mod.rs - source</title><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../../SourceSerif4-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../../FiraSans-Regular.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../../FiraSans-Medium.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../../SourceCodePro-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../../SourceSerif4-Bold.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../../SourceCodePro-Semibold.ttf.woff2"><link rel="stylesheet" href="../../../../normalize.css"><link rel="stylesheet" href="../../../../rustdoc.css" id="mainThemeStyle"><link rel="stylesheet" href="../../../../ayu.css" disabled><link rel="stylesheet" href="../../../../dark.css" disabled><link rel="stylesheet" href="../../../../light.css" id="themeStyle"><script id="default-settings" ></script><script src="../../../../storage.js"></script><script defer src="../../../../source-script.js"></script><script defer src="../../../../source-files.js"></script><script defer src="../../../../main.js"></script><noscript><link rel="stylesheet" href="../../../../noscript.css"></noscript><link rel="alternate icon" type="image/png" href="../../../../favicon-16x16.png"><link rel="alternate icon" type="image/png" href="../../../../favicon-32x32.png"><link rel="icon" type="image/svg+xml" href="../../../../favicon.svg"></head><body class="rustdoc source"><!--[if lte IE 11]><div class="warning">This old browser is unsupported and will most likely display funky things.</div><![endif]--><nav class="sidebar"><a class="sidebar-logo" href="../../../../rusty_machine/index.html"><div class="logo-container"><img class="rust-logo" src="../../../../rust-logo.svg" alt="logo"></div></a></nav><main><div class="width-limiter"><nav class="sub"><a class="sub-logo-container" href="../../../../rusty_machine/index.html"><img class="rust-logo" src="../../../../rust-logo.svg" alt="logo"></a><form class="search-form"><div class="search-container"><span></span><input class="search-input" name="search" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"><div id="help-button" title="help" tabindex="-1"><a href="../../../../help.html">?</a></div><div id="settings-menu" tabindex="-1"><a href="../../../../settings.html" title="settings"><img width="22" height="22" alt="Change settings" src="../../../../wheel.svg"></a></div></div></form></nav><section id="main-content" class="content"><div class="example-wrap"><pre class="src-line-numbers"><span id="1">1</span> |
| <span id="2">2</span> |
| <span id="3">3</span> |
| <span id="4">4</span> |
| <span id="5">5</span> |
| <span id="6">6</span> |
| <span id="7">7</span> |
| <span id="8">8</span> |
| <span id="9">9</span> |
| <span id="10">10</span> |
| <span id="11">11</span> |
| <span id="12">12</span> |
| <span id="13">13</span> |
| <span id="14">14</span> |
| <span id="15">15</span> |
| <span id="16">16</span> |
| <span id="17">17</span> |
| <span id="18">18</span> |
| <span id="19">19</span> |
| <span id="20">20</span> |
| <span id="21">21</span> |
| <span id="22">22</span> |
| <span id="23">23</span> |
| <span id="24">24</span> |
| <span id="25">25</span> |
| <span id="26">26</span> |
| <span id="27">27</span> |
| <span id="28">28</span> |
| <span id="29">29</span> |
| <span id="30">30</span> |
| <span id="31">31</span> |
| <span id="32">32</span> |
| <span id="33">33</span> |
| <span id="34">34</span> |
| <span id="35">35</span> |
| <span id="36">36</span> |
| <span id="37">37</span> |
| <span id="38">38</span> |
| <span id="39">39</span> |
| <span id="40">40</span> |
| <span id="41">41</span> |
| <span id="42">42</span> |
| <span id="43">43</span> |
| <span id="44">44</span> |
| <span id="45">45</span> |
| <span id="46">46</span> |
| <span id="47">47</span> |
| <span id="48">48</span> |
| <span id="49">49</span> |
| <span id="50">50</span> |
| <span id="51">51</span> |
| <span id="52">52</span> |
| <span id="53">53</span> |
| <span id="54">54</span> |
| <span id="55">55</span> |
| <span id="56">56</span> |
| <span id="57">57</span> |
| <span id="58">58</span> |
| <span id="59">59</span> |
| <span id="60">60</span> |
| <span id="61">61</span> |
| <span id="62">62</span> |
| <span id="63">63</span> |
| <span id="64">64</span> |
| <span id="65">65</span> |
| <span id="66">66</span> |
| <span id="67">67</span> |
| <span id="68">68</span> |
| <span id="69">69</span> |
| <span id="70">70</span> |
| <span id="71">71</span> |
| <span id="72">72</span> |
| <span id="73">73</span> |
| <span id="74">74</span> |
| <span id="75">75</span> |
| <span id="76">76</span> |
| <span id="77">77</span> |
| <span id="78">78</span> |
| <span id="79">79</span> |
| <span id="80">80</span> |
| <span id="81">81</span> |
| <span id="82">82</span> |
| <span id="83">83</span> |
| <span id="84">84</span> |
| <span id="85">85</span> |
| <span id="86">86</span> |
| <span id="87">87</span> |
| <span id="88">88</span> |
| <span id="89">89</span> |
| <span id="90">90</span> |
| <span id="91">91</span> |
| <span id="92">92</span> |
| <span id="93">93</span> |
| <span id="94">94</span> |
| <span id="95">95</span> |
| <span id="96">96</span> |
| <span id="97">97</span> |
| <span id="98">98</span> |
| <span id="99">99</span> |
| <span id="100">100</span> |
| <span id="101">101</span> |
| <span id="102">102</span> |
| <span id="103">103</span> |
| <span id="104">104</span> |
| <span id="105">105</span> |
| <span id="106">106</span> |
| <span id="107">107</span> |
| <span id="108">108</span> |
| <span id="109">109</span> |
| <span id="110">110</span> |
| <span id="111">111</span> |
| <span id="112">112</span> |
| <span id="113">113</span> |
| <span id="114">114</span> |
| <span id="115">115</span> |
| <span id="116">116</span> |
| <span id="117">117</span> |
| <span id="118">118</span> |
| <span id="119">119</span> |
| <span id="120">120</span> |
| <span id="121">121</span> |
| <span id="122">122</span> |
| <span id="123">123</span> |
| <span id="124">124</span> |
| <span id="125">125</span> |
| <span id="126">126</span> |
| <span id="127">127</span> |
| <span id="128">128</span> |
| <span id="129">129</span> |
| <span id="130">130</span> |
| <span id="131">131</span> |
| <span id="132">132</span> |
| <span id="133">133</span> |
| <span id="134">134</span> |
| <span id="135">135</span> |
| <span id="136">136</span> |
| <span id="137">137</span> |
| <span id="138">138</span> |
| <span id="139">139</span> |
| <span id="140">140</span> |
| <span id="141">141</span> |
| <span id="142">142</span> |
| <span id="143">143</span> |
| <span id="144">144</span> |
| <span id="145">145</span> |
| <span id="146">146</span> |
| <span id="147">147</span> |
| <span id="148">148</span> |
| <span id="149">149</span> |
| <span id="150">150</span> |
| <span id="151">151</span> |
| <span id="152">152</span> |
| <span id="153">153</span> |
| <span id="154">154</span> |
| <span id="155">155</span> |
| <span id="156">156</span> |
| <span id="157">157</span> |
| <span id="158">158</span> |
| <span id="159">159</span> |
| <span id="160">160</span> |
| <span id="161">161</span> |
| <span id="162">162</span> |
| <span id="163">163</span> |
| <span id="164">164</span> |
| <span id="165">165</span> |
| <span id="166">166</span> |
| <span id="167">167</span> |
| <span id="168">168</span> |
| <span id="169">169</span> |
| <span id="170">170</span> |
| <span id="171">171</span> |
| <span id="172">172</span> |
| <span id="173">173</span> |
| <span id="174">174</span> |
| <span id="175">175</span> |
| <span id="176">176</span> |
| <span id="177">177</span> |
| <span id="178">178</span> |
| <span id="179">179</span> |
| <span id="180">180</span> |
| <span id="181">181</span> |
| <span id="182">182</span> |
| <span id="183">183</span> |
| <span id="184">184</span> |
| <span id="185">185</span> |
| <span id="186">186</span> |
| <span id="187">187</span> |
| <span id="188">188</span> |
| <span id="189">189</span> |
| <span id="190">190</span> |
| <span id="191">191</span> |
| <span id="192">192</span> |
| <span id="193">193</span> |
| <span id="194">194</span> |
| <span id="195">195</span> |
| <span id="196">196</span> |
| <span id="197">197</span> |
| <span id="198">198</span> |
| <span id="199">199</span> |
| <span id="200">200</span> |
| <span id="201">201</span> |
| <span id="202">202</span> |
| <span id="203">203</span> |
| <span id="204">204</span> |
| <span id="205">205</span> |
| <span id="206">206</span> |
| <span id="207">207</span> |
| <span id="208">208</span> |
| <span id="209">209</span> |
| <span id="210">210</span> |
| <span id="211">211</span> |
| <span id="212">212</span> |
| <span id="213">213</span> |
| <span id="214">214</span> |
| <span id="215">215</span> |
| <span id="216">216</span> |
| <span id="217">217</span> |
| <span id="218">218</span> |
| <span id="219">219</span> |
| <span id="220">220</span> |
| <span id="221">221</span> |
| <span id="222">222</span> |
| <span id="223">223</span> |
| <span id="224">224</span> |
| <span id="225">225</span> |
| <span id="226">226</span> |
| <span id="227">227</span> |
| <span id="228">228</span> |
| <span id="229">229</span> |
| <span id="230">230</span> |
| <span id="231">231</span> |
| <span id="232">232</span> |
| <span id="233">233</span> |
| <span id="234">234</span> |
| <span id="235">235</span> |
| <span id="236">236</span> |
| <span id="237">237</span> |
| <span id="238">238</span> |
| <span id="239">239</span> |
| <span id="240">240</span> |
| <span id="241">241</span> |
| <span id="242">242</span> |
| <span id="243">243</span> |
| <span id="244">244</span> |
| <span id="245">245</span> |
| <span id="246">246</span> |
| <span id="247">247</span> |
| <span id="248">248</span> |
| <span id="249">249</span> |
| <span id="250">250</span> |
| <span id="251">251</span> |
| <span id="252">252</span> |
| <span id="253">253</span> |
| <span id="254">254</span> |
| <span id="255">255</span> |
| <span id="256">256</span> |
| <span id="257">257</span> |
| <span id="258">258</span> |
| <span id="259">259</span> |
| <span id="260">260</span> |
| <span id="261">261</span> |
| <span id="262">262</span> |
| <span id="263">263</span> |
| <span id="264">264</span> |
| <span id="265">265</span> |
| <span id="266">266</span> |
| <span id="267">267</span> |
| <span id="268">268</span> |
| <span id="269">269</span> |
| <span id="270">270</span> |
| <span id="271">271</span> |
| <span id="272">272</span> |
| <span id="273">273</span> |
| <span id="274">274</span> |
| <span id="275">275</span> |
| <span id="276">276</span> |
| <span id="277">277</span> |
| <span id="278">278</span> |
| <span id="279">279</span> |
| <span id="280">280</span> |
| <span id="281">281</span> |
| <span id="282">282</span> |
| <span id="283">283</span> |
| <span id="284">284</span> |
| <span id="285">285</span> |
| <span id="286">286</span> |
| <span id="287">287</span> |
| <span id="288">288</span> |
| <span id="289">289</span> |
| <span id="290">290</span> |
| <span id="291">291</span> |
| <span id="292">292</span> |
| <span id="293">293</span> |
| <span id="294">294</span> |
| <span id="295">295</span> |
| <span id="296">296</span> |
| <span id="297">297</span> |
| <span id="298">298</span> |
| <span id="299">299</span> |
| <span id="300">300</span> |
| <span id="301">301</span> |
| <span id="302">302</span> |
| <span id="303">303</span> |
| <span id="304">304</span> |
| <span id="305">305</span> |
| <span id="306">306</span> |
| <span id="307">307</span> |
| <span id="308">308</span> |
| <span id="309">309</span> |
| <span id="310">310</span> |
| <span id="311">311</span> |
| <span id="312">312</span> |
| <span id="313">313</span> |
| <span id="314">314</span> |
| <span id="315">315</span> |
| <span id="316">316</span> |
| <span id="317">317</span> |
| <span id="318">318</span> |
| <span id="319">319</span> |
| <span id="320">320</span> |
| <span id="321">321</span> |
| <span id="322">322</span> |
| <span id="323">323</span> |
| <span id="324">324</span> |
| <span id="325">325</span> |
| <span id="326">326</span> |
| <span id="327">327</span> |
| <span id="328">328</span> |
| <span id="329">329</span> |
| <span id="330">330</span> |
| <span id="331">331</span> |
| <span id="332">332</span> |
| <span id="333">333</span> |
| <span id="334">334</span> |
| <span id="335">335</span> |
| <span id="336">336</span> |
| <span id="337">337</span> |
| <span id="338">338</span> |
| <span id="339">339</span> |
| <span id="340">340</span> |
| <span id="341">341</span> |
| <span id="342">342</span> |
| <span id="343">343</span> |
| <span id="344">344</span> |
| <span id="345">345</span> |
| <span id="346">346</span> |
| <span id="347">347</span> |
| <span id="348">348</span> |
| <span id="349">349</span> |
| <span id="350">350</span> |
| <span id="351">351</span> |
| <span id="352">352</span> |
| <span id="353">353</span> |
| <span id="354">354</span> |
| <span id="355">355</span> |
| <span id="356">356</span> |
| <span id="357">357</span> |
| <span id="358">358</span> |
| <span id="359">359</span> |
| <span id="360">360</span> |
| <span id="361">361</span> |
| <span id="362">362</span> |
| <span id="363">363</span> |
| <span id="364">364</span> |
| <span id="365">365</span> |
| <span id="366">366</span> |
| <span id="367">367</span> |
| <span id="368">368</span> |
| <span id="369">369</span> |
| <span id="370">370</span> |
| <span id="371">371</span> |
| <span id="372">372</span> |
| <span id="373">373</span> |
| <span id="374">374</span> |
| <span id="375">375</span> |
| <span id="376">376</span> |
| <span id="377">377</span> |
| <span id="378">378</span> |
| <span id="379">379</span> |
| <span id="380">380</span> |
| <span id="381">381</span> |
| <span id="382">382</span> |
| <span id="383">383</span> |
| <span id="384">384</span> |
| <span id="385">385</span> |
| <span id="386">386</span> |
| <span id="387">387</span> |
| <span id="388">388</span> |
| <span id="389">389</span> |
| <span id="390">390</span> |
| <span id="391">391</span> |
| <span id="392">392</span> |
| <span id="393">393</span> |
| <span id="394">394</span> |
| <span id="395">395</span> |
| <span id="396">396</span> |
| <span id="397">397</span> |
| <span id="398">398</span> |
| <span id="399">399</span> |
| <span id="400">400</span> |
| <span id="401">401</span> |
| <span id="402">402</span> |
| <span id="403">403</span> |
| <span id="404">404</span> |
| <span id="405">405</span> |
| <span id="406">406</span> |
| <span id="407">407</span> |
| <span id="408">408</span> |
| <span id="409">409</span> |
| <span id="410">410</span> |
| <span id="411">411</span> |
| <span id="412">412</span> |
| <span id="413">413</span> |
| <span id="414">414</span> |
| <span id="415">415</span> |
| <span id="416">416</span> |
| <span id="417">417</span> |
| <span id="418">418</span> |
| <span id="419">419</span> |
| <span id="420">420</span> |
| <span id="421">421</span> |
| <span id="422">422</span> |
| <span id="423">423</span> |
| <span id="424">424</span> |
| <span id="425">425</span> |
| <span id="426">426</span> |
| <span id="427">427</span> |
| <span id="428">428</span> |
| <span id="429">429</span> |
| <span id="430">430</span> |
| <span id="431">431</span> |
| <span id="432">432</span> |
| <span id="433">433</span> |
| <span id="434">434</span> |
| <span id="435">435</span> |
| <span id="436">436</span> |
| <span id="437">437</span> |
| <span id="438">438</span> |
| <span id="439">439</span> |
| <span id="440">440</span> |
| <span id="441">441</span> |
| <span id="442">442</span> |
| <span id="443">443</span> |
| <span id="444">444</span> |
| <span id="445">445</span> |
| <span id="446">446</span> |
| <span id="447">447</span> |
| <span id="448">448</span> |
| <span id="449">449</span> |
| <span id="450">450</span> |
| <span id="451">451</span> |
| <span id="452">452</span> |
| <span id="453">453</span> |
| <span id="454">454</span> |
| <span id="455">455</span> |
| <span id="456">456</span> |
| <span id="457">457</span> |
| <span id="458">458</span> |
| <span id="459">459</span> |
| <span id="460">460</span> |
| <span id="461">461</span> |
| <span id="462">462</span> |
| <span id="463">463</span> |
| <span id="464">464</span> |
| <span id="465">465</span> |
| <span id="466">466</span> |
| <span id="467">467</span> |
| <span id="468">468</span> |
| <span id="469">469</span> |
| <span id="470">470</span> |
| <span id="471">471</span> |
| <span id="472">472</span> |
| <span id="473">473</span> |
| <span id="474">474</span> |
| <span id="475">475</span> |
| <span id="476">476</span> |
| <span id="477">477</span> |
| <span id="478">478</span> |
| <span id="479">479</span> |
| <span id="480">480</span> |
| <span id="481">481</span> |
| <span id="482">482</span> |
| <span id="483">483</span> |
| <span id="484">484</span> |
| <span id="485">485</span> |
| <span id="486">486</span> |
| <span id="487">487</span> |
| <span id="488">488</span> |
| <span id="489">489</span> |
| <span id="490">490</span> |
| <span id="491">491</span> |
| <span id="492">492</span> |
| <span id="493">493</span> |
| <span id="494">494</span> |
| <span id="495">495</span> |
| <span id="496">496</span> |
| <span id="497">497</span> |
| <span id="498">498</span> |
| <span id="499">499</span> |
| <span id="500">500</span> |
| <span id="501">501</span> |
| <span id="502">502</span> |
| <span id="503">503</span> |
| <span id="504">504</span> |
| <span id="505">505</span> |
| <span id="506">506</span> |
| <span id="507">507</span> |
| <span id="508">508</span> |
| <span id="509">509</span> |
| <span id="510">510</span> |
| <span id="511">511</span> |
| <span id="512">512</span> |
| <span id="513">513</span> |
| <span id="514">514</span> |
| <span id="515">515</span> |
| <span id="516">516</span> |
| <span id="517">517</span> |
| <span id="518">518</span> |
| <span id="519">519</span> |
| <span id="520">520</span> |
| <span id="521">521</span> |
| <span id="522">522</span> |
| <span id="523">523</span> |
| <span id="524">524</span> |
| <span id="525">525</span> |
| <span id="526">526</span> |
| <span id="527">527</span> |
| <span id="528">528</span> |
| <span id="529">529</span> |
| <span id="530">530</span> |
| <span id="531">531</span> |
| <span id="532">532</span> |
| <span id="533">533</span> |
| <span id="534">534</span> |
| <span id="535">535</span> |
| <span id="536">536</span> |
| <span id="537">537</span> |
| <span id="538">538</span> |
| <span id="539">539</span> |
| <span id="540">540</span> |
| <span id="541">541</span> |
| <span id="542">542</span> |
| <span id="543">543</span> |
| <span id="544">544</span> |
| <span id="545">545</span> |
| <span id="546">546</span> |
| <span id="547">547</span> |
| <span id="548">548</span> |
| <span id="549">549</span> |
| <span id="550">550</span> |
| <span id="551">551</span> |
| <span id="552">552</span> |
| <span id="553">553</span> |
| <span id="554">554</span> |
| <span id="555">555</span> |
| <span id="556">556</span> |
| <span id="557">557</span> |
| <span id="558">558</span> |
| <span id="559">559</span> |
| <span id="560">560</span> |
| <span id="561">561</span> |
| <span id="562">562</span> |
| <span id="563">563</span> |
| <span id="564">564</span> |
| <span id="565">565</span> |
| <span id="566">566</span> |
| <span id="567">567</span> |
| <span id="568">568</span> |
| <span id="569">569</span> |
| <span id="570">570</span> |
| <span id="571">571</span> |
| <span id="572">572</span> |
| <span id="573">573</span> |
| <span id="574">574</span> |
| <span id="575">575</span> |
| <span id="576">576</span> |
| <span id="577">577</span> |
| <span id="578">578</span> |
| <span id="579">579</span> |
| <span id="580">580</span> |
| <span id="581">581</span> |
| <span id="582">582</span> |
| <span id="583">583</span> |
| <span id="584">584</span> |
| <span id="585">585</span> |
| <span id="586">586</span> |
| <span id="587">587</span> |
| <span id="588">588</span> |
| </pre><pre class="rust"><code><span class="doccomment">//! Neural Network module |
| //! |
| //! Contains implementation of simple feed forward neural network. |
| //! |
| //! # Usage |
| //! |
| //! ``` |
| //! use rusty_machine::learning::nnet::{NeuralNet, BCECriterion}; |
| //! use rusty_machine::learning::toolkit::regularization::Regularization; |
| //! use rusty_machine::learning::toolkit::activ_fn::Sigmoid; |
| //! use rusty_machine::learning::optim::grad_desc::StochasticGD; |
| //! use rusty_machine::linalg::Matrix; |
| //! use rusty_machine::learning::SupModel; |
| //! |
| //! let inputs = Matrix::new(5,3, vec![1.,1.,1.,2.,2.,2.,3.,3.,3., |
| //! 4.,4.,4.,5.,5.,5.,]); |
| //! let targets = Matrix::new(5,3, vec![1.,0.,0.,0.,1.,0.,0.,0.,1., |
| //! 0.,0.,1.,0.,0.,1.]); |
| //! |
| //! // Set the layer sizes - from input to output |
| //! let layers = &[3,5,11,7,3]; |
| //! |
| //! // Choose the BCE criterion with L2 regularization (`lambda=0.1`). |
| //! let criterion = BCECriterion::new(Regularization::L2(0.1)); |
| //! |
| //! // We will create a multilayer perceptron and just use the default stochastic gradient descent. |
| //! let mut model = NeuralNet::mlp(layers, criterion, StochasticGD::default(), Sigmoid); |
| //! |
| //! // Train the model! |
| //! model.train(&inputs, &targets).unwrap(); |
| //! |
| //! let test_inputs = Matrix::new(2,3, vec![1.5,1.5,1.5,5.1,5.1,5.1]); |
| //! |
| //! // And predict new output from the test inputs |
| //! let outputs = model.predict(&test_inputs).unwrap(); |
| //! ``` |
| //! |
| //! The neural networks are specified via a criterion - similar to |
| //! [Torch](https://github.com/torch/nn/blob/master/doc/criterion.md). |
| //! The criterions specify a cost function and any regularization. |
| //! |
| //! You can define your own criterion by implementing the `Criterion` |
| //! trait with a concrete `CostFunc`. |
| |
| |
| </span><span class="kw">pub mod </span>net_layer; |
| |
| <span class="kw">use </span>linalg::{Matrix, MatrixSlice}; |
| <span class="kw">use </span>rulinalg::utils; |
| |
| <span class="kw">use </span>learning::{LearningResult, SupModel}; |
| <span class="kw">use </span>learning::error::{Error, ErrorKind}; |
| <span class="kw">use </span>learning::toolkit::activ_fn; |
| <span class="kw">use </span>learning::toolkit::activ_fn::ActivationFunc; |
| <span class="kw">use </span>learning::toolkit::cost_fn; |
| <span class="kw">use </span>learning::toolkit::cost_fn::CostFunc; |
| <span class="kw">use </span>learning::toolkit::regularization::Regularization; |
| <span class="kw">use </span>learning::optim::{Optimizable, OptimAlgorithm}; |
| <span class="kw">use </span>learning::optim::grad_desc::StochasticGD; |
| |
| <span class="kw">use </span><span class="self">self</span>::net_layer::NetLayer; |
| |
| <span class="doccomment">/// Neural Network Model |
| /// |
| /// The Neural Network struct specifies a `Criterion` and |
| /// a gradient descent algorithm. |
| </span><span class="attribute">#[derive(Debug)] |
| </span><span class="kw">pub struct </span>NeuralNet<T, A> |
| <span class="kw">where </span>T: Criterion, |
| A: OptimAlgorithm<BaseNeuralNet<T>> |
| { |
| base: BaseNeuralNet<T>, |
| alg: A, |
| } |
| |
| <span class="doccomment">/// Supervised learning for the Neural Network. |
| /// |
| /// The model is trained using back propagation. |
| </span><span class="kw">impl</span><T, A> SupModel<Matrix<f64>, Matrix<f64>> <span class="kw">for </span>NeuralNet<T, A> |
| <span class="kw">where </span>T: Criterion, |
| A: OptimAlgorithm<BaseNeuralNet<T>> |
| { |
| <span class="doccomment">/// Predict neural network output using forward propagation. |
| </span><span class="kw">fn </span>predict(<span class="kw-2">&</span><span class="self">self</span>, inputs: <span class="kw-2">&</span>Matrix<f64>) -> LearningResult<Matrix<f64>> { |
| <span class="self">self</span>.base.forward_prop(inputs) |
| } |
| |
| <span class="doccomment">/// Train the model using gradient optimization and back propagation. |
| </span><span class="kw">fn </span>train(<span class="kw-2">&mut </span><span class="self">self</span>, inputs: <span class="kw-2">&</span>Matrix<f64>, targets: <span class="kw-2">&</span>Matrix<f64>) -> LearningResult<()> { |
| <span class="kw">let </span>optimal_w = <span class="self">self</span>.alg.optimize(<span class="kw-2">&</span><span class="self">self</span>.base, <span class="kw-2">&</span><span class="self">self</span>.base.weights, inputs, targets); |
| <span class="self">self</span>.base.weights = optimal_w; |
| <span class="prelude-val">Ok</span>(()) |
| } |
| } |
| |
| <span class="kw">impl </span>NeuralNet<BCECriterion, StochasticGD> { |
| <span class="doccomment">/// Creates a neural network with the specified layer sizes. |
| /// |
| /// The layer sizes slice should include the input, hidden layers, and output layer sizes. |
| /// The type of activation function must be specified. |
| /// |
| /// Uses the default settings (stochastic gradient descent and sigmoid activation function). |
| /// |
| /// # Examples |
| /// |
| /// ``` |
| /// use rusty_machine::learning::nnet::NeuralNet; |
| /// |
| /// // Create a neural net with 4 layers, 3 neurons in each. |
| /// let layers = &[3; 4]; |
| /// let mut net = NeuralNet::default(layers); |
| /// ``` |
| </span><span class="kw">pub fn </span>default(layer_sizes: <span class="kw-2">&</span>[usize]) -> NeuralNet<BCECriterion, StochasticGD> { |
| NeuralNet { |
| base: BaseNeuralNet::default(layer_sizes, activ_fn::Sigmoid), |
| alg: StochasticGD::default(), |
| } |
| } |
| } |
| |
| <span class="kw">impl</span><T, A> NeuralNet<T, A> |
| <span class="kw">where </span>T: Criterion, |
| A: OptimAlgorithm<BaseNeuralNet<T>> |
| { |
| <span class="doccomment">/// Create a new neural network with no layers |
| /// |
| /// # Examples |
| /// |
| /// ``` |
| /// use rusty_machine::learning::nnet::BCECriterion; |
| /// use rusty_machine::learning::nnet::NeuralNet; |
| /// use rusty_machine::learning::optim::grad_desc::StochasticGD; |
| /// |
| /// // Create a an empty neural net |
| /// let mut net = NeuralNet::new(BCECriterion::default(), StochasticGD::default()); |
| /// ``` |
| </span><span class="kw">pub fn </span>new(criterion: T, alg: A) -> NeuralNet<T, A> { |
| NeuralNet { |
| base: BaseNeuralNet::new(criterion), |
| alg: alg, |
| } |
| } |
| |
| <span class="doccomment">/// Create a multilayer perceptron with the specified layer sizes. |
| /// |
| /// The layer sizes slice should include the input, hidden layers, and output layer sizes. |
| /// The type of activation function must be specified. |
| /// |
| /// Currently defaults to simple batch Gradient Descent for optimization. |
| /// |
| /// # Examples |
| /// |
| /// ``` |
| /// use rusty_machine::learning::nnet::BCECriterion; |
| /// use rusty_machine::learning::nnet::NeuralNet; |
| /// use rusty_machine::learning::toolkit::activ_fn::Sigmoid; |
| /// use rusty_machine::learning::optim::grad_desc::StochasticGD; |
| /// |
| /// // Create a neural net with 4 layers, 3 neurons in each. |
| /// let layers = &[3; 4]; |
| /// let mut net = NeuralNet::mlp(layers, BCECriterion::default(), StochasticGD::default(), Sigmoid); |
| /// ``` |
| </span><span class="kw">pub fn </span>mlp<U>(layer_sizes: <span class="kw-2">&</span>[usize], criterion: T, alg: A, activ_fn: U) -> NeuralNet<T, A> |
| <span class="kw">where </span>U: ActivationFunc + <span class="lifetime">'static </span>{ |
| NeuralNet { |
| base: BaseNeuralNet::mlp(layer_sizes, criterion, activ_fn), |
| alg: alg, |
| } |
| } |
| |
| <span class="doccomment">/// Adds the specified layer to the end of the network |
| /// |
| /// # Examples |
| /// |
| /// ``` |
| /// use rusty_machine::linalg::BaseMatrix; |
| /// use rusty_machine::learning::nnet::BCECriterion; |
| /// use rusty_machine::learning::nnet::NeuralNet; |
| /// use rusty_machine::learning::nnet::net_layer::Linear; |
| /// use rusty_machine::learning::optim::grad_desc::StochasticGD; |
| /// |
| /// // Create a new neural net |
| /// let mut net = NeuralNet::new(BCECriterion::default(), StochasticGD::default()); |
| /// |
| /// // Give net an input layer of size 3, hidden layer of size 4, and output layer of size 5 |
| /// // This net will not apply any activation function to the Linear layer outputs |
| /// net.add(Box::new(Linear::new(3, 4))) |
| /// .add(Box::new(Linear::new(4, 5))); |
| /// ``` |
| </span><span class="kw">pub fn </span>add<<span class="lifetime">'a</span>>(<span class="kw-2">&</span><span class="lifetime">'a </span><span class="kw-2">mut </span><span class="self">self</span>, layer: Box<<span class="kw">dyn </span>NetLayer>) -> <span class="kw-2">&</span><span class="lifetime">'a </span><span class="kw-2">mut </span>NeuralNet<T, A> { |
| <span class="self">self</span>.base.add(layer); |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Adds multiple layers to the end of the network |
| /// |
| /// # Examples |
| /// |
| /// ``` |
| /// use rusty_machine::linalg::BaseMatrix; |
| /// use rusty_machine::learning::nnet::BCECriterion; |
| /// use rusty_machine::learning::nnet::NeuralNet; |
| /// use rusty_machine::learning::nnet::net_layer::{NetLayer, Linear}; |
| /// use rusty_machine::learning::toolkit::activ_fn::Sigmoid; |
| /// use rusty_machine::learning::optim::grad_desc::StochasticGD; |
| /// |
| /// // Create a new neural net |
| /// let mut net = NeuralNet::new(BCECriterion::default(), StochasticGD::default()); |
| /// |
| /// let linear_sig: Vec<Box<NetLayer>> = vec![Box::new(Linear::new(5, 5)), Box::new(Sigmoid)]; |
| /// |
| /// // Give net a layer of size 5, followed by a Sigmoid activation function |
| /// net.add_layers(linear_sig); |
| /// ``` |
| </span><span class="kw">pub fn </span>add_layers<<span class="lifetime">'a</span>, U>(<span class="kw-2">&</span><span class="lifetime">'a </span><span class="kw-2">mut </span><span class="self">self</span>, layers: U) -> <span class="kw-2">&</span><span class="lifetime">'a </span><span class="kw-2">mut </span>NeuralNet<T, A> |
| <span class="kw">where </span>U: IntoIterator<Item = Box<<span class="kw">dyn </span>NetLayer>> { |
| <span class="self">self</span>.base.add_layers(layers); |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Gets matrix of weights between specified layer and forward layer. |
| /// |
| /// # Examples |
| /// |
| /// ``` |
| /// use rusty_machine::linalg::BaseMatrix; |
| /// use rusty_machine::learning::nnet::NeuralNet; |
| /// |
| /// // Create a neural net with 4 layers, 3 neurons in each. |
| /// let layers = &[3; 4]; |
| /// let mut net = NeuralNet::default(layers); |
| /// |
| /// let w = &net.get_net_weights(2); |
| /// |
| /// // We add a bias term to the weight matrix |
| /// assert_eq!(w.rows(), 4); |
| /// assert_eq!(w.cols(), 3); |
| /// ``` |
| </span><span class="kw">pub fn </span>get_net_weights(<span class="kw-2">&</span><span class="self">self</span>, idx: usize) -> MatrixSlice<f64> { |
| <span class="self">self</span>.base.get_layer_weights(<span class="kw-2">&</span><span class="self">self</span>.base.weights[..], idx) |
| } |
| } |
| |
| <span class="doccomment">/// Base Neural Network struct |
| /// |
| /// This struct cannot be instantiated and is used internally only. |
| </span><span class="attribute">#[derive(Debug)] |
| </span><span class="kw">pub struct </span>BaseNeuralNet<T: Criterion> { |
| layers: Vec<Box<<span class="kw">dyn </span>NetLayer>>, |
| weights: Vec<f64>, |
| criterion: T, |
| } |
| |
| |
| <span class="kw">impl </span>BaseNeuralNet<BCECriterion> { |
| <span class="doccomment">/// Creates a base neural network with the specified layer sizes. |
| </span><span class="kw">fn </span>default<U>(layer_sizes: <span class="kw-2">&</span>[usize], activ_fn: U) -> BaseNeuralNet<BCECriterion> |
| <span class="kw">where </span>U: ActivationFunc + <span class="lifetime">'static </span>{ |
| BaseNeuralNet::mlp(layer_sizes, BCECriterion::default(), activ_fn) |
| } |
| } |
| |
| |
| <span class="kw">impl</span><T: Criterion> BaseNeuralNet<T> { |
| <span class="doccomment">/// Create a base neural network with no layers |
| </span><span class="kw">fn </span>new(criterion: T) -> BaseNeuralNet<T> { |
| BaseNeuralNet { |
| layers: Vec::new(), |
| weights: Vec::new(), |
| criterion: criterion |
| } |
| } |
| |
| <span class="doccomment">/// Create a multilayer perceptron with the specified layer sizes. |
| </span><span class="kw">fn </span>mlp<U>(layer_sizes: <span class="kw-2">&</span>[usize], criterion: T, activ_fn: U) -> BaseNeuralNet<T> |
| <span class="kw">where </span>U: ActivationFunc + <span class="lifetime">'static </span>{ |
| <span class="kw">let </span><span class="kw-2">mut </span>mlp = BaseNeuralNet { |
| layers: Vec::with_capacity(<span class="number">2</span><span class="kw-2">*</span>(layer_sizes.len()-<span class="number">1</span>)), |
| weights: Vec::new(), |
| criterion: criterion |
| }; |
| <span class="kw">for </span>shape <span class="kw">in </span>layer_sizes.windows(<span class="number">2</span>) { |
| mlp.add(Box::new(net_layer::Linear::new(shape[<span class="number">0</span>], shape[<span class="number">1</span>]))); |
| mlp.add(Box::new(activ_fn.clone())); |
| } |
| mlp |
| } |
| |
| <span class="doccomment">/// Adds the specified layer to the end of the network |
| </span><span class="kw">fn </span>add<<span class="lifetime">'a</span>>(<span class="kw-2">&</span><span class="lifetime">'a </span><span class="kw-2">mut </span><span class="self">self</span>, layer: Box<<span class="kw">dyn </span>NetLayer>) -> <span class="kw-2">&</span><span class="lifetime">'a </span><span class="kw-2">mut </span>BaseNeuralNet<T> { |
| <span class="self">self</span>.weights.extend_from_slice(<span class="kw-2">&</span>layer.default_params()); |
| <span class="self">self</span>.layers.push(layer); |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Adds multiple layers to the end of the network |
| </span><span class="kw">fn </span>add_layers<<span class="lifetime">'a</span>, U>(<span class="kw-2">&</span><span class="lifetime">'a </span><span class="kw-2">mut </span><span class="self">self</span>, layers: U) -> <span class="kw-2">&</span><span class="lifetime">'a </span><span class="kw-2">mut </span>BaseNeuralNet<T> |
| <span class="kw">where </span>U: IntoIterator<Item = Box<<span class="kw">dyn </span>NetLayer>> |
| { |
| <span class="kw">for </span>layer <span class="kw">in </span>layers { |
| <span class="self">self</span>.add(layer); |
| } |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Gets matrix of weights for the specified layer for the weights. |
| </span><span class="kw">fn </span>get_layer_weights(<span class="kw-2">&</span><span class="self">self</span>, weights: <span class="kw-2">&</span>[f64], idx: usize) -> MatrixSlice<f64> { |
| <span class="macro">debug_assert!</span>(idx < <span class="self">self</span>.layers.len()); |
| |
| <span class="comment">// Check that the weights are the right size. |
| </span><span class="kw">let </span>full_size: usize = <span class="self">self</span>.layers.iter().map(|l| l.num_params()).sum(); |
| |
| <span class="macro">debug_assert_eq!</span>(full_size, weights.len()); |
| |
| <span class="kw">let </span>start: usize = <span class="self">self</span>.layers.iter().take(idx).map(|l| l.num_params()).sum(); |
| |
| <span class="kw">let </span>shape = <span class="self">self</span>.layers[idx].param_shape(); |
| <span class="kw">unsafe </span>{ |
| MatrixSlice::from_raw_parts(weights.as_ptr().offset(start <span class="kw">as </span>isize), |
| shape.<span class="number">0</span>, |
| shape.<span class="number">1</span>, |
| shape.<span class="number">1</span>) |
| } |
| } |
| |
| <span class="doccomment">/// Compute the gradient using the back propagation algorithm. |
| </span><span class="kw">fn </span>compute_grad(<span class="kw-2">&</span><span class="self">self</span>, |
| weights: <span class="kw-2">&</span>[f64], |
| inputs: <span class="kw-2">&</span>Matrix<f64>, |
| targets: <span class="kw-2">&</span>Matrix<f64>) |
| -> (f64, Vec<f64>) { |
| <span class="kw">let </span><span class="kw-2">mut </span>gradients = Vec::with_capacity(weights.len()); |
| <span class="kw">unsafe </span>{ |
| gradients.set_len(weights.len()); |
| } |
| <span class="comment">// activations[i] is the output of layer[i] |
| </span><span class="kw">let </span><span class="kw-2">mut </span>activations = Vec::with_capacity(<span class="self">self</span>.layers.len()); |
| <span class="comment">// params[i] is the weights for layer[i] |
| </span><span class="kw">let </span><span class="kw-2">mut </span>params = Vec::with_capacity(<span class="self">self</span>.layers.len()); |
| |
| <span class="comment">// Forward propagation |
| |
| </span><span class="kw">let </span><span class="kw-2">mut </span>index = <span class="number">0</span>; |
| <span class="kw">for </span>(i, layer) <span class="kw">in </span><span class="self">self</span>.layers.iter().enumerate() { |
| <span class="kw">let </span>shape = layer.param_shape(); |
| |
| <span class="kw">let </span>slice = <span class="kw">unsafe </span>{ |
| MatrixSlice::from_raw_parts(weights.as_ptr().offset(index <span class="kw">as </span>isize), |
| shape.<span class="number">0</span>, |
| shape.<span class="number">1</span>, |
| shape.<span class="number">1</span>) |
| }; |
| |
| <span class="kw">let </span>output = <span class="kw">if </span>i == <span class="number">0 </span>{ |
| layer.forward(inputs, slice).unwrap() |
| } <span class="kw">else </span>{ |
| layer.forward(activations.last().unwrap(), slice).unwrap() |
| }; |
| |
| activations.push(output); |
| params.push(slice); |
| index += layer.num_params(); |
| } |
| <span class="kw">let </span>output = activations.last().unwrap(); |
| |
| <span class="comment">// Backward propagation |
| |
| // The gradient with respect to the current layer's output |
| </span><span class="kw">let </span><span class="kw-2">mut </span>out_grad = <span class="self">self</span>.criterion.cost_grad(output, targets); |
| <span class="comment">// at this point index == weights.len() |
| </span><span class="kw">for </span>(i, layer) <span class="kw">in </span><span class="self">self</span>.layers.iter().enumerate().rev() { |
| <span class="kw">let </span>activation = <span class="kw">if </span>i == <span class="number">0 </span>{inputs} <span class="kw">else </span>{<span class="kw-2">&</span>activations[i-<span class="number">1</span>]}; |
| <span class="kw">let </span>result = <span class="kw-2">&</span>activations[i]; |
| index -= layer.num_params(); |
| |
| <span class="kw">let </span>grad_params = <span class="kw-2">&mut </span>gradients[index..index+layer.num_params()]; |
| grad_params.copy_from_slice(layer.back_params(<span class="kw-2">&</span>out_grad, activation, result, params[i]).data()); |
| |
| out_grad = layer.back_input(<span class="kw-2">&</span>out_grad, activation, result, params[i]); |
| } |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>cost = <span class="self">self</span>.criterion.cost(output, targets); |
| <span class="kw">if </span><span class="self">self</span>.criterion.is_regularized() { |
| <span class="kw">let </span>all_params = <span class="kw">unsafe </span>{ |
| MatrixSlice::from_raw_parts(weights.as_ptr(), weights.len(), <span class="number">1</span>, <span class="number">1</span>) |
| }; |
| utils::in_place_vec_bin_op(<span class="kw-2">&mut </span>gradients, |
| <span class="self">self</span>.criterion.reg_cost_grad(all_params).data(), |
| |x, <span class="kw-2">&</span>y| <span class="kw-2">*</span>x = <span class="kw-2">*</span>x + y); |
| cost += <span class="self">self</span>.criterion.reg_cost(all_params); |
| } |
| (cost, gradients) |
| } |
| |
| <span class="doccomment">/// Forward propagation of the model weights to get the outputs. |
| </span><span class="kw">fn </span>forward_prop(<span class="kw-2">&</span><span class="self">self</span>, inputs: <span class="kw-2">&</span>Matrix<f64>) -> LearningResult<Matrix<f64>> { |
| <span class="kw">if </span><span class="self">self</span>.layers.is_empty() { |
| <span class="kw">return </span><span class="prelude-val">Ok</span>(inputs.clone()); |
| } |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>outputs = <span class="kw">unsafe </span>{ |
| <span class="kw">let </span>shape = <span class="self">self</span>.layers[<span class="number">0</span>].param_shape(); |
| <span class="kw">let </span>slice = MatrixSlice::from_raw_parts(<span class="self">self</span>.weights.as_ptr(), |
| shape.<span class="number">0</span>, |
| shape.<span class="number">1</span>, |
| shape.<span class="number">1</span>); |
| <span class="self">self</span>.layers[<span class="number">0</span>].forward(inputs, slice)<span class="question-mark">? |
| </span>}; |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>index = <span class="self">self</span>.layers[<span class="number">0</span>].num_params(); |
| <span class="kw">for </span>layer <span class="kw">in </span><span class="self">self</span>.layers.iter().skip(<span class="number">1</span>) { |
| <span class="kw">let </span>shape = layer.param_shape(); |
| |
| <span class="kw">let </span>slice = <span class="kw">unsafe </span>{ |
| MatrixSlice::from_raw_parts(<span class="self">self</span>.weights.as_ptr().offset(index <span class="kw">as </span>isize), |
| shape.<span class="number">0</span>, |
| shape.<span class="number">1</span>, |
| shape.<span class="number">1</span>) |
| }; |
| |
| outputs = <span class="kw">match </span>layer.forward(<span class="kw-2">&</span>outputs, slice) { |
| <span class="prelude-val">Ok</span>(act) => act, |
| <span class="prelude-val">Err</span>(<span class="kw">_</span>) => {<span class="kw">return </span><span class="prelude-val">Err</span>(Error::new(ErrorKind::InvalidParameters, |
| <span class="string">"The network's layers do not line up correctly."</span>))} |
| }; |
| |
| index += layer.num_params(); |
| } |
| <span class="prelude-val">Ok</span>(outputs) |
| } |
| } |
| |
| <span class="doccomment">/// Compute the gradient of the Neural Network using the |
| /// back propagation algorithm. |
| </span><span class="kw">impl</span><T: Criterion> Optimizable <span class="kw">for </span>BaseNeuralNet<T> { |
| <span class="kw">type </span>Inputs = Matrix<f64>; |
| <span class="kw">type </span>Targets = Matrix<f64>; |
| |
| <span class="doccomment">/// Compute the gradient of the neural network. |
| </span><span class="kw">fn </span>compute_grad(<span class="kw-2">&</span><span class="self">self</span>, |
| params: <span class="kw-2">&</span>[f64], |
| inputs: <span class="kw-2">&</span>Matrix<f64>, |
| targets: <span class="kw-2">&</span>Matrix<f64>) |
| -> (f64, Vec<f64>) { |
| <span class="self">self</span>.compute_grad(params, inputs, targets) |
| } |
| } |
| |
| <span class="doccomment">/// Criterion for Neural Networks |
| /// |
| /// Specifies an activation function and a cost function. |
| </span><span class="kw">pub trait </span>Criterion { |
| <span class="doccomment">/// The cost function for the criterion. |
| </span><span class="kw">type </span>Cost: CostFunc<Matrix<f64>>; |
| |
| <span class="doccomment">/// The cost function. |
| /// |
| /// Returns a scalar cost. |
| </span><span class="kw">fn </span>cost(<span class="kw-2">&</span><span class="self">self</span>, outputs: <span class="kw-2">&</span>Matrix<f64>, targets: <span class="kw-2">&</span>Matrix<f64>) -> f64 { |
| <span class="self">Self</span>::Cost::cost(outputs, targets) |
| } |
| |
| <span class="doccomment">/// The gradient of the cost function. |
| /// |
| /// Returns a matrix of cost gradients. |
| </span><span class="kw">fn </span>cost_grad(<span class="kw-2">&</span><span class="self">self</span>, outputs: <span class="kw-2">&</span>Matrix<f64>, targets: <span class="kw-2">&</span>Matrix<f64>) -> Matrix<f64> { |
| <span class="self">Self</span>::Cost::grad_cost(outputs, targets) |
| } |
| |
| <span class="doccomment">/// Returns the regularization for this criterion. |
| /// |
| /// Will return `Regularization::None` by default. |
| </span><span class="kw">fn </span>regularization(<span class="kw-2">&</span><span class="self">self</span>) -> Regularization<f64> { |
| Regularization::None |
| } |
| |
| <span class="doccomment">/// Checks if the current criterion includes regularization. |
| /// |
| /// Will return `false` by default. |
| </span><span class="kw">fn </span>is_regularized(<span class="kw-2">&</span><span class="self">self</span>) -> bool { |
| <span class="kw">match </span><span class="self">self</span>.regularization() { |
| Regularization::None => <span class="bool-val">false</span>, |
| <span class="kw">_ </span>=> <span class="bool-val">true</span>, |
| } |
| } |
| |
| <span class="doccomment">/// Returns the regularization cost for the criterion. |
| /// |
| /// Will return `0` by default. |
| /// |
| /// This method will not be invoked by the neural network |
| /// if there is explicitly no regularization. |
| </span><span class="kw">fn </span>reg_cost(<span class="kw-2">&</span><span class="self">self</span>, reg_weights: MatrixSlice<f64>) -> f64 { |
| <span class="self">self</span>.regularization().reg_cost(reg_weights) |
| } |
| |
| <span class="doccomment">/// Returns the regularization gradient for the criterion. |
| /// |
| /// Will return a matrix of zeros by default. |
| /// |
| /// This method will not be invoked by the neural network |
| /// if there is explicitly no regularization. |
| </span><span class="kw">fn </span>reg_cost_grad(<span class="kw-2">&</span><span class="self">self</span>, reg_weights: MatrixSlice<f64>) -> Matrix<f64> { |
| <span class="self">self</span>.regularization().reg_grad(reg_weights) |
| } |
| } |
| |
| <span class="doccomment">/// The binary cross entropy criterion. |
| /// |
| /// Uses the Sigmoid activation function and the |
| /// cross entropy error. |
| </span><span class="attribute">#[derive(Clone, Copy, Debug)] |
| </span><span class="kw">pub struct </span>BCECriterion { |
| regularization: Regularization<f64>, |
| } |
| |
| <span class="kw">impl </span>Criterion <span class="kw">for </span>BCECriterion { |
| <span class="kw">type </span>Cost = cost_fn::CrossEntropyError; |
| |
| <span class="kw">fn </span>regularization(<span class="kw-2">&</span><span class="self">self</span>) -> Regularization<f64> { |
| <span class="self">self</span>.regularization |
| } |
| } |
| |
| <span class="doccomment">/// Creates an MSE Criterion without any regularization. |
| </span><span class="kw">impl </span>Default <span class="kw">for </span>BCECriterion { |
| <span class="kw">fn </span>default() -> <span class="self">Self </span>{ |
| BCECriterion { regularization: Regularization::None } |
| } |
| } |
| |
| <span class="kw">impl </span>BCECriterion { |
| <span class="doccomment">/// Constructs a new BCECriterion with the given regularization. |
| /// |
| /// # Examples |
| /// |
| /// ``` |
| /// use rusty_machine::learning::nnet::BCECriterion; |
| /// use rusty_machine::learning::toolkit::regularization::Regularization; |
| /// |
| /// // Create a new BCE criterion with L2 regularization of 0.3. |
| /// let criterion = BCECriterion::new(Regularization::L2(0.3f64)); |
| /// ``` |
| </span><span class="kw">pub fn </span>new(regularization: Regularization<f64>) -> <span class="self">Self </span>{ |
| BCECriterion { regularization: regularization } |
| } |
| } |
| |
| <span class="doccomment">/// The mean squared error criterion. |
| /// |
| /// Uses the Linear activation function and the |
| /// mean squared error. |
| </span><span class="attribute">#[derive(Clone, Copy, Debug)] |
| </span><span class="kw">pub struct </span>MSECriterion { |
| regularization: Regularization<f64>, |
| } |
| |
| <span class="kw">impl </span>Criterion <span class="kw">for </span>MSECriterion { |
| <span class="kw">type </span>Cost = cost_fn::MeanSqError; |
| |
| <span class="kw">fn </span>regularization(<span class="kw-2">&</span><span class="self">self</span>) -> Regularization<f64> { |
| <span class="self">self</span>.regularization |
| } |
| } |
| |
| <span class="doccomment">/// Creates an MSE Criterion without any regularization. |
| </span><span class="kw">impl </span>Default <span class="kw">for </span>MSECriterion { |
| <span class="kw">fn </span>default() -> <span class="self">Self </span>{ |
| MSECriterion { regularization: Regularization::None } |
| } |
| } |
| |
| <span class="kw">impl </span>MSECriterion { |
| <span class="doccomment">/// Constructs a new BCECriterion with the given regularization. |
| /// |
| /// # Examples |
| /// |
| /// ``` |
| /// use rusty_machine::learning::nnet::MSECriterion; |
| /// use rusty_machine::learning::toolkit::regularization::Regularization; |
| /// |
| /// // Create a new MSE criterion with L2 regularization of 0.3. |
| /// let criterion = MSECriterion::new(Regularization::L2(0.3f64)); |
| /// ``` |
| </span><span class="kw">pub fn </span>new(regularization: Regularization<f64>) -> <span class="self">Self </span>{ |
| MSECriterion { regularization: regularization } |
| } |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../../../" data-current-crate="rusty_machine" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |
