機(jī)器學(xué)習(xí) 深度學(xué)習(xí) ai

Artificial Intelligence (AI) will and is currently taking over an important role in our lives — not necessarily through intelligent robots — but a learning algorithm is implemented in many intelligent technologies. Also, Machine Learning and Deep Learning are contemporary important terms in Computer Science. But those AI-related terms are often mixed up or falsely taken as synonyms, which will be clarified in the following.

人工智能(AI)將并且目前正在我們的生活中扮演重要角色，不一定通過(guò)智能機(jī)器人，而是許多智能技術(shù)中都采用了學(xué)習(xí)算法。 此外，機(jī)器學(xué)習(xí)和深度學(xué)習(xí)也是計(jì)算機(jī)科學(xué)中的當(dāng)代重要術(shù)語(yǔ)。 但是那些與AI相關(guān)的術(shù)語(yǔ)經(jīng)常被混淆或錯(cuò)誤地當(dāng)作同義詞，這將在下文中闡明。

The word “intelligence” alone is quite hard to define. One can try it through probably the most popular method: The Turing Test. It argues that intelligence can be identified behavior-based. For instance, regarding a chat-bot, one could say: If it is undistinguishable if the chat partner is a human or computer, the computer can be entitled as “intelligent”, even if it is just an imitation game without any awareness on the computer’s side. Consequently, intelligence has not necessarily something to do with human intelligence. The term Artificial Intelligence was primarily introduced by John McCarthy in 1956 offering a seminar with this as a title. He is therefore often referred to as the Father of AI. He stated: “The study is to proceed on the basis of the conjecture that 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” and therefore sets a first stone in characterizing Artificial Intelligence. Initially, Machine Learning was not separated from the field of AI, which changed in the 1990s: The scientists started to tackle practical problems and went away from symbolic approaches regarding intelligence. The term of Deep Learning appeared in the year 2000 for the first time describing an Artificial Neural Network.

僅“智能”一詞很難定義。 可以嘗試通過(guò)最流行的方法進(jìn)行嘗試：圖靈測(cè)試。 它認(rèn)為可以將智能識(shí)別為基于行為的。 例如，對(duì)于一個(gè)聊天機(jī)器人，人們可能會(huì)說(shuō)：如果聊天伙伴是人還是計(jì)算機(jī)，如果無(wú)法區(qū)分它，則該計(jì)算機(jī)可以被稱(chēng)為“智能”，即使它只是一個(gè)模仿游戲，而對(duì)它卻沒(méi)有任何了解。電腦方面。 因此，情報(bào)不一定與人類(lèi)情報(bào)有關(guān)。 人工智能一詞最初是由約翰·麥卡錫(John McCarthy)在1956年提出的，當(dāng)時(shí)以研討會(huì)為標(biāo)題。 因此，他經(jīng)常被稱(chēng)為AI之父。 他說(shuō)：“這項(xiàng)研究是基于這樣的猜想，即原則上可以精確地描述學(xué)習(xí)的各個(gè)方面或智力的任何其他特征，從而可以制造出可以模擬它的機(jī)器”，因此奠定了基礎(chǔ)。表征人工智能。 最初，機(jī)器學(xué)習(xí)并沒(méi)有脫離AI領(lǐng)域，而AI領(lǐng)域在1990年代發(fā)生了變化：科學(xué)家們開(kāi)始解決實(shí)際問(wèn)題，并擺脫了有關(guān)智能的象征性方法。 深度學(xué)習(xí)這個(gè)詞首次出現(xiàn)在2000年，描述了人工神經(jīng)網(wǎng)絡(luò)。

什么是人工智能？ (What is Artificial Intelligence?)

Everyone might have some applications in mind coming from utopias presented in film and fiction or media. AI is basically working with a goal, which is trying to enable machines to make decisions. As already mentioned, the word intelligence can be misleading. Therefore, we now want to go back to the basics trying to bring the fundamental idea of these technologies to you by using examples. One popular example is using oranges and apples. The goal is to teach the machine what an apple and an orange look like and enabling it to separate them. Each fruit has certain features, which have to be told to the algorithm: An apple is red or green, whereas an orange is orange. It has a bumpy surface, while the apple is smooth. Translated to English, you implement in the algorithm: “If something is red or green, is round and has a smooth texture, you call it an apple” and “If something is orange, round and has a bumpy texture you call it an orange”. And this is the first step one must take when it comes to programming an AI-powered software. If the software now recognizes the mentioned features, it can give the output “orange” or “apple”. As a code it looks like this:

每個(gè)人可能都會(huì)想到來(lái)自電影，小說(shuō)或媒體中呈現(xiàn)的烏托邦的某些應(yīng)用。 人工智能基本上是與一個(gè)目標(biāo)合作，該目標(biāo)試圖使機(jī)器做出決策。 如前所述，“情報(bào)”一詞可能會(huì)引起誤解。 因此，我們現(xiàn)在想回到基礎(chǔ)知識(shí)，嘗試通過(guò)使用示例將這些技術(shù)的基本思想帶給您。 一個(gè)流行的例子是使用橘子和蘋(píng)果。 目的是教會(huì)機(jī)器蘋(píng)果和橘子的外觀，并使它們分開(kāi)。 每個(gè)水果都有某些特征，必須告知算法：蘋(píng)果是紅色或綠色，而橙色是橙色。 它表面凹凸不平，蘋(píng)果光滑。 翻譯成英文，您可以在算法中實(shí)現(xiàn)：“如果某物是紅色或綠色，圓形并且具有光滑的紋理，則稱(chēng)其為蘋(píng)果”和“如果某物是橙色，圓形并且具有凹凸不平的紋理，則稱(chēng)其為橙色” ”。 這是編程基于AI的軟件時(shí)必須采取的第一步。 如果該軟件現(xiàn)在能夠識(shí)別上述功能，則可以將輸出設(shè)為“橙色”或“蘋(píng)果”。 作為代碼，它看起來(lái)像這樣：

In this code certain features of oranges and apples are defined在此代碼中，定義了橘子和蘋(píng)果的某些功能

We can set: Artificial Intelligence means enabling a machine to think and mimic human behavior as it is now possible to take its own decisions.

我們可以設(shè)置：人工智能意味著使機(jī)器能夠思考和模仿人類(lèi)的行為，因?yàn)楝F(xiàn)在可以自行決定。

什么是機(jī)器學(xué)習(xí)？ (What is Machine Learning?)

The algorithm can now decide, whether it is seeing an orange or an apple, because we taught the software what the features of each fruit are and therefore enabled it to decide on its own. This is all fun and games until you cut the orange into eatable pieces. A human can still recognize the apple as apple, but how should the software be able to do it when it goes by an apple being round? It cannot. Now you give the software many pictures of apples in different angles, cut in pieces or in different color shades and add information: Those are all apples. Of course, it is the same with categorizing oranges. The software can now recognize apples and oranges in almost every shape — depending on the amount of data given. How much data is needed as minimum is depending on the application, but there are some good clues. At a bare minimum there should be around 1,000 examples. For average problems with mid complexity 10,000 to 100,000 examples are needed. Regarding the amount of data one can conject: The more the better. Machine Learning is therefore not only about decisions, but rather about being able to broaden your horizon.

該算法現(xiàn)在可以確定是看到橙色還是蘋(píng)果，這是因?yàn)槲覀兘塘嗽撥浖糠N水果的特征，因此可以自行決定。 直到您將橙子切成可食用的塊，這都是有趣的游戲。 人們?nèi)匀豢梢詫⑻O(píng)果識(shí)別為蘋(píng)果，但是當(dāng)蘋(píng)果變圓時(shí)，該軟件應(yīng)該如何做到呢？ 這不可以。 現(xiàn)在，您可以為該軟件提供許多不同角度的蘋(píng)果圖片，切成薄片或以不同的顏色陰影添加信息：這些都是蘋(píng)果。 當(dāng)然，對(duì)橘子進(jìn)行分類(lèi)也是一樣。 該軟件現(xiàn)在可以識(shí)別幾乎每種形狀的蘋(píng)果和橙子-取決于給定的數(shù)據(jù)量。 最少需要多少數(shù)據(jù)取決于應(yīng)用程序，但是有一些很好的線(xiàn)索。 最少應(yīng)該有大約1,000個(gè)示例。 對(duì)于中等復(fù)雜度的平均問(wèn)題，需要10,000至100,000個(gè)示例。 關(guān)于人們可以推測(cè)的數(shù)據(jù)量：越多越好。 因此，機(jī)器學(xué)習(xí)不僅與決策有關(guān)，而且還與拓寬視野有關(guān)。

We can set: Machine Learning is a statistical tool that enables the machine to learn from given data or experience.

我們可以設(shè)置：機(jī)器學(xué)習(xí)是一種統(tǒng)計(jì)工具，可使機(jī)器從給定的數(shù)據(jù)或經(jīng)驗(yàn)中學(xué)習(xí)。

什么是深度學(xué)習(xí)？ (What is Deep Learning?)

As all important inventions of humankind, the field of AI also uses nature as a role model. Deep Learning (DL) is working through a Deep Neural Network orienting itself on the human brain. The Artificial Networks are built with different layers consisting of connected neurons. Each layer can have a special purpose, for example learning to detect patterns in the data, which enables it to recognize objects as the same ones. Another function can be looking for specific pre-set patterns, like a round, red or green object with a smooth surface and considering it as an apple. The information that this is called an apple must be given by human help. Whereas finding out that it is still an apple, even if one half is in the shadow, is something that can be learned unsupervised (without human help) by the algorithm through training data. One should mention that an Artificial Network is not nearly as complicated as a natural one and is not on a human-level intelligent or thinking human-like. Regarding the information processing there are no electrical or chemical impulses rather than a signal being zero or one. But it is indeed inspired by nature and transferred to technology: While a single neuron is not capable of doing something, a whole Neural Network is extremely complex. The behavior of the system is determined by the ways how the neurons are wired together. Each neuron reacts to the incoming signals in a specific way that can also adapt over time. DL is for example also applied in Language Processing. The Artificial Network analyses parts of the speech, like sentence structure, specific word-use or phrases. This allows the algorithm to do natural Language Processing (NLP) and puts the human-machine interaction on a whole new level. This means having a chat with a computer feels like talking to a human.

作為人類(lèi)的所有重要發(fā)明，人工智能領(lǐng)域也將自然作為榜樣。 深度學(xué)習(xí)(DL)正在通過(guò)將深度神經(jīng)網(wǎng)絡(luò)定位在人腦上的功能。 人工網(wǎng)絡(luò)由連接神經(jīng)元的不同層構(gòu)成。 每一層都可以有特殊的用途，例如學(xué)習(xí)檢測(cè)數(shù)據(jù)中的模式，從而使其能夠?qū)?duì)象識(shí)別為相同的對(duì)象。 另一個(gè)功能是尋找特定的預(yù)設(shè)圖案，例如表面光滑的圓形，紅色或綠色物體，并將其視為蘋(píng)果。 稱(chēng)為蘋(píng)果的信息必須由人工幫助提供。 而即使有一半被發(fā)現(xiàn)，它仍然是一個(gè)蘋(píng)果，這是算法可以通過(guò)訓(xùn)練數(shù)據(jù)在無(wú)監(jiān)督的情況下(無(wú)需人工幫助)學(xué)習(xí)的東西。 應(yīng)該提到的是，人工網(wǎng)絡(luò)并不像自然網(wǎng)絡(luò)那樣復(fù)雜，也不是在人類(lèi)層面的智能或類(lèi)似人類(lèi)的思維上。 關(guān)于信息處理，沒(méi)有電或化學(xué)脈沖，而不是信號(hào)為零或一。 但這確實(shí)是受自然啟發(fā)并轉(zhuǎn)移到技術(shù)上的：雖然單個(gè)神經(jīng)元無(wú)法做某事，但整個(gè)神經(jīng)網(wǎng)絡(luò)卻極其復(fù)雜。 系統(tǒng)的行為取決于神經(jīng)元如何連接在一起的方式。 每個(gè)神經(jīng)元都以特定的方式對(duì)傳入的信號(hào)做出React，這種方式也可以隨著時(shí)間的流逝而適應(yīng)。 例如，DL也應(yīng)用于語(yǔ)言處理。 人工網(wǎng)絡(luò)分析語(yǔ)音的某些部分，例如句子結(jié)構(gòu)，特定的單詞用法或短語(yǔ)。 這使算法可以進(jìn)行自然語(yǔ)言處理(NLP)，并將人機(jī)交互提升到一個(gè)全新的水平。 這意味著與計(jì)算機(jī)聊天就像在和人聊天。

We can set: Deep Learning is enabling the machine to mimic the human brain through artificial neurons and therefore can identify important features on its own.

我們可以設(shè)置：深度學(xué)習(xí)使機(jī)器能夠通過(guò)人造神經(jīng)元模仿人類(lèi)的大腦，因此可以自行識(shí)別重要特征。

全部連接 (It is all connected)

There is basically no common definition of Artificial Intelligence and sometimes it is hard to decide whether something can be called Artificial Intelligence or not. Each of the mentioned technologies are connected and part of each other: Deep Learning is a part of Machine Learning, which itself is a part of Artificial Intelligence.

人工智能基本上沒(méi)有通用的定義，有時(shí)很難確定是否可以稱(chēng)為人工智能。 每種提及的技術(shù)都是相互聯(lián)系的，并且是彼此的一部分：深度學(xué)習(xí)是機(jī)器學(xué)習(xí)的一部分，而機(jī)器學(xué)習(xí)本身是人工智能的一部分。

Deep Learning is considered to be a part of Machine Learning, while it is a part of Artificial Learning深度學(xué)習(xí)被認(rèn)為是機(jī)器學(xué)習(xí)的一部分，而它是人工學(xué)習(xí)的一部分

?Going one step back, the word “intelligence” alone is quite hard to define. As explained previously, the Turing Test is a common method. It argues, that something can be identified as intelligent only due to its behavior. Regarding a chat-bot one could say that if it is indistinguishable if it is a human or computer on the other side, the behavior could be determined as “intelligent”, even if it is just an imitation game without any awareness on the computer’s side. And we remember: Even an Artificial Neural Network is only orienting on its natural role model, but is not truly comparable to one. Every intelligent outcome a computer provides is based on the training data given. As mentioned previously regarding the training data one can conject: The more relevant data, the better. This is where the field of AI is related to Data Science. Even the best software-code in the world is worth nothing without sufficient data to learn from it.

向后退一步，僅“智能”一詞很難定義。 如前所述，圖靈測(cè)試是一種常用方法。 它認(rèn)為，只有某種事物的行為才能被認(rèn)為是智能的。 關(guān)于聊天機(jī)器人，可以說(shuō)，如果它是另一端是人還是計(jì)算機(jī)，如果無(wú)法區(qū)分它，則該行為可以被確定為“智能”，即使它只是一個(gè)模仿游戲，而對(duì)計(jì)算機(jī)也沒(méi)有任何了解。 。 我們還記得：即使是人工神經(jīng)網(wǎng)絡(luò)也僅以其自然的榜樣為導(dǎo)向，但并不能真正與之媲美。 計(jì)算機(jī)提供的每一個(gè)智能結(jié)果都是基于給定的訓(xùn)練數(shù)據(jù)。 如前所述，關(guān)于訓(xùn)練數(shù)據(jù)，人們可以推測(cè)：相關(guān)數(shù)據(jù)越多越好。 這就是AI領(lǐng)域與數(shù)據(jù)科學(xué)相關(guān)的地方。 沒(méi)有足夠的數(shù)據(jù)來(lái)學(xué)習(xí)，即使是世界上最好的軟件代碼也一文不值。

Artificial Intelligence is a part of Data Science人工智能是數(shù)據(jù)科學(xué)的一部分

方法和問(wèn)題 (?Methods and problems)

For Deep Learning we are data-wise not talking about a bare minimum of around 1,000 examples, but rather around 100,000 to 1,000,000 examples to learn from. We are now getting into Big Data spheres in the field of Data Science. This term is also connected to the field of Artificial Intelligence in the way of AI being a part of Data Science. Since one cannot always offer this amount of data, the principle of heuristics can be pulled up. This method uses the information it has and estimates an outcome for the next step based on that. Taking chess-playing as a popular example, the program has the value and position of all figures as input and therefore can predict possible outcomes like losing a figure or winning the game. Despite this is often enough to solve a problem, it is no precise solution. The human brain uses the concept of heuristics daily, hence this is another aspect, where nature as role model can be noticed.

對(duì)于深度學(xué)習(xí)，我們?cè)跀?shù)據(jù)方面并不是在談?wù)撝辽偌s1,000個(gè)示例，而是要從中學(xué)習(xí)100,000至1,000,000個(gè)示例。 我們現(xiàn)在正在進(jìn)入數(shù)據(jù)科學(xué)領(lǐng)域的大數(shù)據(jù)領(lǐng)域。 該術(shù)語(yǔ)也通過(guò)AI作為數(shù)據(jù)科學(xué)的一部分與人工智能領(lǐng)域相關(guān)聯(lián)。 由于不能總是提供這么多的數(shù)據(jù)，因此啟發(fā)式原理可以被提出。 該方法使用所擁有的信息，并據(jù)此估算下一步的結(jié)果。 以國(guó)際象棋為例，該程序?qū)⑺腥宋锏膬r(jià)值和位置作為輸入，因此可以預(yù)測(cè)可能的結(jié)果，例如失去人物或贏得比賽。 盡管這通常足以解決問(wèn)題，但這并不是精確的解決方案。 人腦每天都使用啟發(fā)式的概念，因此這是另一個(gè)方面，可以注意到自然作為榜樣。

Besides self-driving cars and image processing of oranges and apples as an example, the state-of-the-art applications are already integrated in our daily lives. For instance, in streaming services each personal recommendation is based on AI-driven algorithms using your data. Here, another example that can be added to the picture processing of our fruit salad: The nearest neighbor classification. Here, the habits of each user are tracked: What kind of movies or series did he or her watch and how did he or her rate them? And now the algorithm compares all users to each other, assuming that people having similar consuming habits might like the same kind of content. For both applications one thing is sure: There is a huge amount of data needed — the more, the better. Hence, the less training data is available the worse is the software’s performance, which is is considered as huge problem for many applications.

除了無(wú)人駕駛汽車(chē)和橘子和蘋(píng)果的圖像處理以外，最先進(jìn)的應(yīng)用程序已經(jīng)集成到我們的日常生活中。 例如，在流媒體服務(wù)中，每個(gè)個(gè)人推薦都基于使用數(shù)據(jù)的AI驅(qū)動(dòng)算法。 在這里，可以添加到水果沙拉的圖片處理中的另一個(gè)示例：最近鄰居分類(lèi)。 在此，可以跟蹤每個(gè)用戶(hù)的習(xí)慣：他或她觀看了哪種電影或電視劇，以及他們?nèi)绾卧u(píng)價(jià)它們？ 現(xiàn)在，該算法將所有用戶(hù)相互比較，并假設(shè)有相似消費(fèi)習(xí)慣的人們可能喜歡相同類(lèi)型的內(nèi)容。 對(duì)于這兩個(gè)應(yīng)用程序，可以肯定的是：需要大量的數(shù)據(jù)-越多越好。 因此，可用的訓(xùn)練數(shù)據(jù)越少，軟件的性能就越差，這對(duì)于許多應(yīng)用程序來(lái)說(shuō)是一個(gè)巨大的問(wèn)題。

渴望獲得更多知識(shí) (Hunger for more knowledge)

If you want to learn more about Artificial Intelligence and do some research on Artificial Intelligence, we can recommend a free and open AI online course developed by the University of Helsinki. It is the AI researchers’ aim to educate at least 1% of the world’s society about Artificial Intelligence.

如果您想了解有關(guān)人工智能的更多信息并進(jìn)行人工智能研究，我們可以推薦由赫爾辛基大學(xué)開(kāi)發(fā)的免費(fèi)開(kāi)放的AI在線(xiàn)課程 。 AI研究人員的目標(biāo)是教育全世界至少1％的人工智能知識(shí)。

翻譯自: https://medium.com/swlh/artificial-intelligence-machine-learning-deep-learning-characteristics-and-differences-ddb4bda470c4

機(jī)器學(xué)習(xí) 深度學(xué)習(xí) ai

總結(jié)

以上是生活随笔為你收集整理的机器学习 深度学习 ai_人工智能，机器学习，深度学习-特征和差异的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺(jué)得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。