Machine Learning

Spread the love

Machine Learning

機器學習
這系列 Machine Learning 教學文章,將帶您了解人工智慧、機器學習、深度學習的差異、該怎麼選擇資料訓練機器學習系統、以及機器學習系統又是如何被訓練的?

Machine Learning

  • 人工智慧 (Artificial Intelligence);
  • 機器學習 (Machine Learning);
  • 深度學習(Deep Learning)。

人工智慧 (Artificial Intelligence)
人工智慧
什麼是人工智慧?

人工智慧 (AI) 是能讓事物變更聰明的科技,我們可以這樣定義:「讓機器展現人類的智慧。」它是一個能讓電腦執行人類工作的廣義術語,而人工智慧的範圍眾說紛紜,隨著時間推衍產生更多的應用和變化。

人工智慧在哪裡?

現今所執行的系統是一種弱人工智慧的形式 – 系統可以做一件或是多件事情,而做的程度與人類相當,甚至超越人類。比如說我們透過寫程式碼來創建學習系統,訓練它辨識物體或是手勢。舉例來說:自然語言處理、電子遊戲行為的人工智慧、機器學習都是弱人工智慧的形式。

人工智慧:常見使用案例
  • 物體識別
  • 語音識別 / 聲波探測
  • 自然語言處理 / 語意分析
  • 創造力
    風格轉換 – 學習用藝術家的風格繪畫
  • 預測
    當輸入未曾見過的例子時,預測所得到的輸出是什麼
  • 語言翻譯
  • 修復 / 轉換
    利用機器學習來判斷一張照片中存在著什麼物件,或是對照片進行人臉辨識

機器學習 (Machine Learning)
機器學習
什麼是機器學習?

機器學習(ML)通常可以這樣定義:「透過從過往的資料和經驗中學習並找到其運行規則,最後達到人工智慧的方法。」

機器學習包含透過樣本訓練機器辨識出運作模式,而不是用特定的規則來編程。這些樣本可以在資料中找到。換句話說,機器學習是一種弱人工智慧(narrow AI),它從資料中得到複雜的函數(或樣本)來學習以創造演算法(或一組規則),並利用它來做預測。

從例子中學習

機器學習是關於如何預測未來。它透過以下的方式去進行訓練:

  • 它需要資料(去訓練系統)
  • 從資料中學習樣本
  • 根據步驟2所獲得的經驗,替未曾見過的新資料做分類,並推測它可能是什麼

機器學習的厲害之處在於它可以自主學習。現在的機器學習應用都做得不錯,比如識別物件,同樣的 ML 系統仍然可以使用在未來的物件,並不需要重寫程式碼,這是相當方便且強大的。


深度學習 (Deep Learning)
什麼是深度學習?

深度學習

深度學習 (DL)可以這樣被定義:「一種實現機器學習的技術。」

這樣的DL技術被稱為深度神經網絡(deep neural networks – DNNs)。在DNNs的情況下,深度學習本質上就是DL所在的代碼結構,它們被安排在鬆散地模仿人類大腦的圖層中,學習模式中的模式(learning patterns of patterns)。

總結
人工智慧這個概念可以追溯到1950年代,是相當長的一段時間。到了1980年,機器學習開始越來越受歡迎。大約到了2010年,DL在弱人工智慧系統方面有了重大的進展。你可以發現這三個詞彼此之間的聯繫 – 基本上是彼此的子集。深度學習驅動機器學習,最後實現了人工智慧。


全新 Digital Marketing 體驗,請聯絡 Web 仔


IT 及增值服務:創建網站推廣行銷開立公司


AI測謊

重蹈偽科學歷史覆轍? 但是,這些看似複雜

0 comments

AI崛起:被取代的職業

【Cheers】在不久的將來,容易被AI

0 comments

TensorFlow:強大的機器學習框架

【Medium】今天早晨,我發現我正從在

0 comments

深度學習:有幾「深」?

一文搞懂深度學習 深度學習 其實跟 VR

0 comments

無人駕駛

許多科技公司、汽車大廠無不投入 無人駕駛

0 comments

Top 7 Machine Learning Methods

Every Data Scientist

0 comments


Insight Machine Learning

  • How to Calculate Feature Importance With Python
    by Jason Brownlee on 29/03/2020 at 18:00

    Feature importance refers to techniques that assign a score to input features based on how useful they are at predicting a target variable. There are many types and sources of feature importance scores, although popular examples include statistical correlation scores, coefficients calculated as part of linear models, decision trees, and permutation importance scores. Feature importance The post How to Calculate Feature Importance With Python appeared first on Machine Learning Mastery.

  • White House, Hospitals, Private Companies Exploring AI to Fight Coronavirus
    by Benjamin Ross on 26/03/2020 at 21:30

    By John P. Desmond, AI Trends Editor The White House has issued a “call to action” to AI researchers to help fight the coronavirus spread; hospitals are pursuing AI to help manage the outbreak, and a number of companies are engaged in research to apply AI to the fight. Here is an update. The White

  • Executive Interview: Beena Ammanath Boosts Women and Diversity in Tech as AI Expands
    by Benjamin Ross on 26/03/2020 at 21:30

    Putting Guardrails in Place for Women and Diversity in Tech as AI Is Infused Into Everything in the Organization Beena Ammanath is the Founder and CEO of Humans For AI, a nonprofit organization focused on increasing diversity in tech leveraging AI. She is a recognized lead and industry expert who has driven pioneering technology changes

  • Clinical Data Sharing for AI: Proposed Framework Could Rouse Debate
    by Benjamin Ross on 26/03/2020 at 21:30

    By Deb Borfitz, Senior Science Writer A group of doctors from Stanford University has proposed a framework for sharing clinical data for artificial intelligence (AI) that could set off a firestorm of debate about who truly owns medical data, ethical obligations to share it, and how to properly police researchers who use it. On the

  • Quantum Computing with AI Seen Helping to Advance IoT
    by Benjamin Ross on 26/03/2020 at 21:30

    By AI Trends Staff While still in a development stage, quantum computing is starting to advance into a new era, where it is poised to accelerate AI and the Internet of Things. Quantum computing is seen as helping us to address some of the biggest and most complex challenges we face as humans, suggested author

Open chat
創建網站
Hi, 我係Web仔, 有乜野可以幫你?
Powered by