Edit "neural-networks (chinese)" by @dzhou1221 (#493)

* Edit "neural-networks (chinese)" by @dzhou1221

* Edit "neural-networks (chinese)" by @dzhou1221

* Edit "neural-networks (chinese)" by @dzhou1221

2017/neural-networks/chinese/description.json

@@ -129,4 +129,4 @@
   "translatedText": "",
   "n_reviews": 0
  }
-]
+]

2017/neural-networks/chinese/sentence_translations.json

@@ -1,26 +1,26 @@
 [
  {
   "input": "This is a 3.",
-  "translatedText": "这是一个 3.",
+  "translatedText": "这是一个 数字3.",
   "model": "DeepL",
-  "n_reviews": 0,
+  "n_reviews": 1,
   "start": 4.22,
   "end": 5.4
  },
  {
   "input": "It's sloppily written and rendered at an extremely low resolution of 28x28 pixels, but your brain has no trouble recognizing it as a 3.",
-  "translatedText": "虽然文字潦草，分辨率也极低，仅为 28x28 像素，但你的大脑却能准确地将其识别为 3。",
+  "translatedText": "虽然文字潦草，分辨率也极低，仅为 28x28 像素，但你的大脑却能很轻松地将其识别为 3。",
   "model": "DeepL",
-  "n_reviews": 0,
+  "n_reviews": 1,
   "start": 6.06,
   "end": 13.72
  },
  {
   "input": "And I want you to take a moment to appreciate how crazy it is that brains can do this so effortlessly.",
-  "translatedText": "我希望你们花一点时间来体会一下，大脑能如此毫不费力地做到这一点是多么疯狂。",
+  "translatedText": "我希望你们花一点时间来体会一下，大脑能毫不费力地做到这一点是多么疯狂。",
   "model": "DeepL",
   "from_community_srt": "这 是一个3 一个字迹歪斜 28x28像素 超低分辨率的3 但你的大脑把它辨认成3 一点问题也没有 我希望大家能稍微感叹一下 人脑\"竟然\"能如此轻而易举地完成这项工作 你看这个 这个 和这个图 我们都认作3",
-  "n_reviews": 0,
+  "n_reviews": 1,
   "start": 14.34,
   "end": 18.96
  },
@@ -399,7 +399,7 @@
   "translatedText": "当然，这只是把问题往下推移，因为你如何识别这些子组件，甚至了解正确的子组件应该是什么？",
   "model": "DeepL",
   "n_reviews": 0,
-  "start": 401.0,
+  "start": 401,
   "end": 407.64
  },
  {
@@ -627,7 +627,7 @@
   "model": "DeepL",
   "from_community_srt": "它又叫logistic/逻辑斯蒂曲线 简而言之 它能把非常大的负值变成接近0 非常大的正值变成接近1 而在取值0附近则是平稳增长的 所以这个神经元中的激活值 实际上就是一个对加权和到底有多正的打分",
   "n_reviews": 0,
-  "start": 638.0,
+  "start": 638,
   "end": 646.6
  },
  {
@@ -836,7 +836,7 @@
   "model": "DeepL",
   "n_reviews": 0,
   "start": 821.38,
-  "end": 838.0
+  "end": 838
  },
  {
   "input": "What that means is that taking the weighted sum of the activations in the first layer according to these weights corresponds to one of the terms in the matrix vector product of everything we have on the left here.",
@@ -853,7 +853,7 @@
   "model": "DeepL",
   "from_community_srt": "顺带一句 机器学习到头来和线性代数是不分家的 如果大家想更形象地理解矩阵和矩阵乘法的意义的话 不妨去看下我之前做的线代本质系列吧 特别是第三章 回到符号表达的话题 表达偏置值的时候 我们并不会把一个个值都拎出来单独讨论",
   "n_reviews": 0,
-  "start": 854.0,
+  "start": 854,
   "end": 868.6
  },
  {
@@ -996,7 +996,7 @@
   "translatedText": "据我所知，早期的网络会利用这一点，将相关的加权和压入 0 和 1 之间的区间，你知道这是由神经元要么不活跃要么活跃的生物类比所激发的。",
   "model": "DeepL",
   "n_reviews": 0,
-  "start": 1014.0,
+  "start": 1014,
   "end": 1021.9
  },
  {
@@ -1125,4 +1125,4 @@
   "start": 1105.1,
   "end": 1105.64
  }
-]
+]

2017/neural-networks/chinese/title.json

@@ -2,4 +2,4 @@
  "input": "But what is a neural network? | Chapter 1, Deep learning",
  "translatedText": "但什么是神经网络？ |第一章，深度学习",
  "n_reviews": 0
-}
+}