<ruby id="bdb3f"></ruby>

    <p id="bdb3f"><cite id="bdb3f"></cite></p>

      <p id="bdb3f"><cite id="bdb3f"><th id="bdb3f"></th></cite></p><p id="bdb3f"></p>
        <p id="bdb3f"><cite id="bdb3f"></cite></p>

          <pre id="bdb3f"></pre>
          <pre id="bdb3f"><del id="bdb3f"><thead id="bdb3f"></thead></del></pre>

          <ruby id="bdb3f"><mark id="bdb3f"></mark></ruby><ruby id="bdb3f"></ruby>
          <pre id="bdb3f"><pre id="bdb3f"><mark id="bdb3f"></mark></pre></pre><output id="bdb3f"></output><p id="bdb3f"></p><p id="bdb3f"></p>

          <pre id="bdb3f"><del id="bdb3f"><progress id="bdb3f"></progress></del></pre>

                <ruby id="bdb3f"></ruby>

                ??一站式輕松地調用各大LLM模型接口,支持GPT4、智譜、豆包、星火、月之暗面及文生圖、文生視頻 廣告
                # [神經網絡計算異或]() 首先介紹 ## 1、“和”操作: x1, x2 ∈ {0, 1} y = x1 AND x2 有 hθ(x)\=g(?30+20x1+20x2) ![](https://img.kancloud.cn/34/0b/340b1b8c24d673c4b3e43a72864c52b8_306x32.png) ![](https://img.kancloud.cn/36/f0/36f0270bd76096ff447861ae6a55d7c9_952x791.jpg) 其中g()是sigmoid函數,其圖示如下 ![](https://img.kancloud.cn/ce/8b/ce8b32f8cab731bd8de3d2aa48eebfa7_1257x830.jpg) 當z=4.6時,函數值約為0.99;當z=-4.6時,函數值約為0.01 計算 x1x2h(x)00g(-30)≈001g(-10)≈010g(-10)≈011g(10)≈1 ![](https://img.kancloud.cn/cb/63/cb63f7500eb9a20f49f822dccccc8503_338x306.png) 然后是 ## 2、“或”操作 有 hθ(x)\=g(?10+20x1+20x2) ![](https://img.kancloud.cn/f7/d7/f7d7eab9aab4904d11209a513901de00_309x32.png) ![](https://img.kancloud.cn/fe/13/fe13f2a80a100ea2e88c02ff544ada0e_952x791.jpg) x1x2h(x)000011101111 ![](https://img.kancloud.cn/a9/8f/a98fea3c17f6308e6814eafa4fd39fe7_265x289.png) 然后是 ## 3、“非”操作 ![](https://img.kancloud.cn/e0/14/e0146f38ba8d671f9413bac54be04231_952x498.jpg) 有 hθ(x)\=g(10?20x1) 計算 x1h(x)0110 (當 x==0時, h(x)==1; 當 x==1時,h(x)==0;不用解釋)。 那么“非x1和非x2”如下圖 ![](https://img.kancloud.cn/30/85/308523a8f464f9fafd7d7b2090253296_952x791.jpg) * * * ## 4、最后計算“異或” ![](https://img.kancloud.cn/07/87/0787d1e0b76f200b1ac16e2e5d4b965b_1286x871.jpg) 計算 x1x2a1(2)a2(2)hθ(x)00011010001000011101 ![](https://img.kancloud.cn/af/e9/afe9312718cad4c3007b1464d471b278_491x315.png) * 如果算上輸入層我們的網絡共有三層,如下圖所示,其中第1層和第2層中的1分別是這兩層的偏置單元。連線上是連接前后層的參數。 ![](https://img.kancloud.cn/2f/c5/2fc5f3139159ba66103bdc0a9d38f8d9_753x498.png) * 輸入:我們一共有四個訓練樣本,每個樣本有兩個特征,分別是(0, 0), (1, 0), (0, 1), (1, 1); * 理想輸出:參考上面的真值表,樣本中兩個特征相同時為0,相異為1 * 參數:隨機初始化,范圍為(-1, 1) * ## 5、“同或”,并且總結: ![](https://img.kancloud.cn/4c/d6/4cd6bd19c03fb60816820a278b8637b0_623x341.png) 分類: [machine learning 相關](https://www.cnblogs.com/qkloveslife/category/1319459.html)
                  <ruby id="bdb3f"></ruby>

                  <p id="bdb3f"><cite id="bdb3f"></cite></p>

                    <p id="bdb3f"><cite id="bdb3f"><th id="bdb3f"></th></cite></p><p id="bdb3f"></p>
                      <p id="bdb3f"><cite id="bdb3f"></cite></p>

                        <pre id="bdb3f"></pre>
                        <pre id="bdb3f"><del id="bdb3f"><thead id="bdb3f"></thead></del></pre>

                        <ruby id="bdb3f"><mark id="bdb3f"></mark></ruby><ruby id="bdb3f"></ruby>
                        <pre id="bdb3f"><pre id="bdb3f"><mark id="bdb3f"></mark></pre></pre><output id="bdb3f"></output><p id="bdb3f"></p><p id="bdb3f"></p>

                        <pre id="bdb3f"><del id="bdb3f"><progress id="bdb3f"></progress></del></pre>

                              <ruby id="bdb3f"></ruby>

                              哎呀哎呀视频在线观看