元記事 (Source): Understanding the differences between AI, machine learning, and deep learning - TechRepublic


Understanding the differences between AI, machine learning, and deep learning



Artificial intelligence, machine learning, and deep learning have become integral for many businesses. But, the terms are often used interchangeably. Here's how to tell them apart.


  • integral [形] 不可欠な
  • interchangeably [副] 入れ替えて


With huge strides in AI—from advances in the driverless vehicle realm, to mastering games such as poker and Go, to automating customer service interactions—this advanced technology is poised to revolutionize businesses. But the terms AI, machine learning, and deep learning are often used haphazardly and interchangeably, when there are key differences between each type of technology. Here's a guide to the differences between these three tools to help you master machine intelligence.


  • stride(s) [名] 進歩、発展
  • realm [名] 領域、分野
  • be poised to 〜する用意ができている、〜する構えだ
  • haphazardly [副] でたらめに


Artificial Intelligence (AI)

AI is the broadest way to think about advanced, computer intelligence. In 1956 at the Dartmouth Artificial Intelligence Conference, the technology was described as such: "Every aspect of learning or any other feature of intelligence can in principle be so precisely described that a machine can be made to simulate it.”



AI can refer to anything from a computer program playing a game of chess, to a voice-recognition system like Amazon's Alexa interpreting and responding to speech. The technology can broadly be categorized into three groups: Narrow AI, artificial general intelligence (AGI), and superintelligent AI.

チェスをプレイするプログラムから、通訳したり会話で返事をしたりできるAmazon Alexaのような音声認識システムまで、AIというと様々なものを引き合いに出すことになる。このテクノロジーは広義では3つのカテゴリーに分けることができる。弱いAI(特化型AI、Narrow AI)、人工汎用知能(AGI)、そしてスーパーインテリジェンス(superintelligent AI)だ。

  • refer [動] 参照する、言及する、引き合いに出す


IBM's Deep Blue, which beat chess grand master Garry Kasparov at the game in 1996, or Google DeepMind's AlphaGo, which in 2016 beat Lee Sedol at Go, are examples of narrow AI—AI that is skilled at one specific task. This is different from artificial general intelligence (AGI), which is AI that is considered human-level, and can perform a range of tasks.

IBMのDeep Blue(1996年にチェスのグランドマスターであるGarry Kasparovを倒した)や、Google DeepMind社によるAlphaGo(2016年に囲碁でLee Sedolを倒した)は弱いAI(特化型AI)の一例だ。このAIはある特定の作業が得意である。これは、様々な作業ができて人間レベルの知能と言われる、人工汎用知能(AGI)とは異なるものだ。


Superintelligent AI takes things a step further. As Nick Bostrom describes it, this is "an intellect that is much smarter than the best human brains in practically every field, including scientific creativity, general wisdom and social skills." In other words, it's when the machines have outsmarted us.

スーパー・インテリジェンス(Superintelligent AI)は物事をさらに進歩させる。スーパー・インテリジェンスは「科学的な創造性、全体的な知恵、社交能力を含む全ての分野において、人間の最も優れた知能よりはるかに賢い」とNick Bostromは説明しており、すなわち、これは機械が我々を出し抜く瞬間を意味する。

  • intellect [名] 知性
  • outsmart [動] 出し抜く、裏をかく

Machine Learning (ML)

Machine learning is one subfield of AI. The core principle here is that machines take data and "learn" for themselves. It's currently the most promising tool in the AI kit for businesses. ML systems can quickly apply knowledge and training from large data sets to excel at facial recognition, speech recognition, object recognition, translation, and many other tasks. Unlike hand-coding a software program with specific instructions to complete a task, ML allows a system to learn to recognize patterns on its own and make predictions.


  • excel (at) [動] 冴える、優れる、卓越する


While Deep Blue and DeepMind are both types of AI, Deep Blue was rule-based, dependent on programming—so it was not a form of ML. DeepMind, on the other hand, is: It beat the world champion in Go by training itself on a large data set of expert moves.

Deep BlueとDeepMindはいずれもAIの一種であるが、Deep Blueは人によるプログラミングに依存しているルール・ベースAIであり、ML形式ではない。一方で囲碁の世界チャンピオンを倒したDeepMindは、大量のプロ囲碁棋士棋譜データセットによって自らトレーニングする。


Is your business interested in integrating machine learning into its strategy? Amazon, Baidu, Google, IBM, Microsoft and others offer machine learning platforms that businesses can use.


Deep Learning

Deep learning is a subset of ML. It uses some ML techniques to solve real-world problems by tapping into neural networks that simulate human decision-making. Deep learning can be expensive, and requires massive datasets to train itself on. That's because there are a huge number of parameters that need to be understood by a learning algorithm, which can initially produce a lot of false-positives. For instance, a deep learning algorithm could be instructed to "learn" what a cat looks like. It would take a very massive data set of images for it to understand the very minor details that distinguish a cat from, say, a cheetah or a panther or a fox.


  • tap into 〜を利用する、〜との関係をもつ
  • false-positive 誤判定

As mentioned above, in March 2016, a major AI victory was achieved when DeepMind's AlphaGo program beat world champion Lee Sedol in 4 out of 5 games of Go using deep learning. The way the deep learning system worked was by combining "Monte-Carlo tree search with deep neural networks that have been trained by supervised learning, from human expert games, and by reinforcement learning from games of self-play," according to Google.

前述の通り、2016年5月、DeepMind社のAlphaGoプログラムが囲碁ディープラーニングを使って、世界チャンピオンLee Sedol を5回中4回勝ち越した時、AIの偉大な勝利が達成された。Googleによると、ディープラーニングを機能させる方法は、「人間のプロの対戦を用いた『教師あり学習』で訓練されたディープニューラルネットワークによる『モンテカルロ木探索』と、セルフプレイによる補強」を組み合わせること」だという。


Deep learning also has business applications. It can take a huge amount of data—millions of images, for example—and recognize certain characteristics. Text-based searches, fraud detection, spam detection, handwriting recognition, image search, speech recognition, Street View detection, and translation are all tasks that can be performed through deep learning. At Google, deep learning networks have replaced many "handcrafted rule-based systems," for instance.


  • fraud [名] 詐欺


Deep learning is also highly susceptible to bias. When Google's facial recognition system was initially rolled out, for instance, it tagged many black faces as gorillas. "That's an example of what happens if you have no African American faces in your training set," said Anu Tewary, chief data officer for Mint at Intuit. "If you have no African Americans working on the product. If you have no African Americans testing the product. When your technology encounters African American faces, it's not going to know how to behave."

ディープラーニングは非常にバイアスの影響を受けやすい。例えば、Googleの顔認識システムが公開された当初、非常に多くの黒人の顔をゴリラとタグ付けしてしまった。「これは黒人のアメリカ人の画像がトレーニング用のデータセットなかった場合に起こることの一例だ。」とIntuit社のMintでチーフ・データ・オフィサーを務めるAnu Tewaryは言う。「もし黒人があなたのプロダクトチームで働いてなかった場合、黒人の画像でプロダクトをテストしなかった場合、あなたのテクノロジーは黒人の顔に出会ったとき、どう振る舞ったらよいかわからなくなる」

  • susceptible [形] 影響を受けやすい
  • roll out 公開する、公表する


Some also believe that deep learning is overhyped. Sundown AI, for instance, has mastered automated customer interactions using a combination of ML and policy graph algorithms—not deep learning.

人によってはディープラーニングは誇張されているとも考えている。例えば、Sundown AI社は自動カスタマーインタラクションをディープラーニングではなく、マシンラーニングとpolicy graph algorithmsによってマスターした。

  • overhype [動] 誇大広告する