January 2019
Beginner to intermediate
576 pages
14h 31m
Chinese
Content preview from 深度學習｜內行人的做法
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
深度網路的一般架構原則
|
103
• 平方損失函數
• 邏輯損失函數
• 樞紐（Hinge）損失函數
• 負對數可能性函數
之前我們把損失函數區分成三大類：
• 迴歸損失函數
• 分類損失函數
• 重建損失函數
我們在第 1 章曾介紹過前兩種類型。第三種重建損失函數牽涉到無監督特徵提取，它可
說是深度學習網路達到破記錄正確率的重要原因。在深度網路的某些架構中，若搭配適
當的激活函數，重建損失函數就可以更有效幫助網路提取出特徵。其中一個例子就是把
多分類交叉熵（multiclass cross-entropy）當成損失函數，用於 softmax 激活函數層中，
藉以獲取分類輸出。下一節我們就會介紹這個特別的損失函數。
重建交叉熵損失函數
如果採用的是重建交叉熵損失函數，我們會先套用「高斯雜訊」（這是一種統計白雜
訊），然後損失函數就會懲罰網路中任何與原始輸入資料不相似的結果。這麼一來，就
會促使網路學習不同的特徵，試圖更有效重建輸入，並以最大程度降低誤差。在深度
學習領域中，只要是牽涉到 RBM 預訓練階段的特徵工程，就會用到重建交叉熵損失
函數。
最佳化演算法
以機器學習方式訓練一個模型，其實就是為模型參數向量找出最好的一組值。我們可以
把機器學習視為一種最佳化問題；我們會設法調整模型預測函數的參數，盡可能讓損失
函數最小化。
用損失函數來定義「最佳」
在最佳化演算法中，我們把參數向量「最佳」的一組值，定義成損失函數
最低值所對應的一組值。
104
|
第三章：深度網路基礎
我們曾在第 1 章介紹過最佳化、梯度遞減與參數向量的基本概念 ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.