走向烏托邦的未來 (Towards a utopian future)

The past decade has seen an intense hype about the promising future of artificial intelligence (AI). A future where automation would create a dearth of human jobs by replacing them with AI based systems. The objective of making this utopian dream a reality is encouraging industry as well as academia, to invest towards the research and development of AI based systems. Terms like Machine Learning (ML), Deep Learning(DL) and AI can be frequently encountered in application and research based publications. Improvements in computing power and storage, and the undergoing developments of GPU based libraries have facilitated the use of these methods. However, these terms muddle a lot of people and are sometimes used interchangeably. Therefore, before delving into the amazing prospects of these automated systems, one needs to understand what these terms mean and how are they related/correlated to one another.

在過去的十年中，人們對人工智能(AI)的光明前景進行了大肆宣傳。 未來，自動化將通過基于AI的系統代替人工來創造大量人工工作。 實現這個烏托邦夢想的目標是鼓勵行業和學術界投資于基于AI的系統的研發。 諸如機器學習(ML)，深度學習(DL)和AI之類的術語在基于應用程序和研究的出版物中經常遇到。 計算能力和存儲的改進以及基于GPU的庫的不斷發展促進了這些方法的使用。 但是，這些術語使很多人感到困惑，有時可以互換使用。 因此，在深入研究這些自動化系統的驚人前景之前，需要了解這些術語的含義以及它們之間的關系/相關性。

邁向自動化智能：過去，現在和未來 (Towards Automated Intelligence: Past, present and future)

The term ‘Artificial Intelligence’ came into existence in the 1950s when researchers in the domain of computer science starting pondering over the possibility of “making computers think”. In other words, would it be possible to automate intellectual tasks performed by humans? Most of the research in AI is centered around five different components: learning, reasoning, problem-solving, perception, and language-understanding. To achieve these objectives researchers have proposed a number of tools, some of which we are going to discuss in this article:

“人工智能”一詞在1950年代問世，當時計算機科學領域的研究人員開始思考“讓計算機思考”的可能性。 換句話說，是否有可能使人類執行的智力任務自動化？ 人工智能的大多數研究都圍繞五個不同的方面：學習，推理，解決問題，感知和語言理解。 為了實現這些目標，研究人員提出了許多工具，本文將討論其中一些：

Symbolic AI

象征性AI

Symbolic AI (Haugeland, John (1985)) was the earliest forms is AI (1950–1980) that researchers believed could help achieve human-level intelligence by explicitly hardcoding the rules to manipulate data (IBM’s Deep Blue vs chess champion Kasparov, 1997). But could machines go beyond performing tasks which we already know how to perform? In other words, can a machine learn different patterns and behaviours by themselves without any set of hardcoded rules? This question paved way for a new

象征性AI( Haugeland，John (1985))最早的形式是AI(1950–1980)，研究人員認為它可以通過對規則進行硬編碼來操縱數據來幫助實現人類智能(IBM Deep Blue vs國際象棋冠軍Kasparov，1997)。 。 但是，機器能否超越執行我們已經知道如何執行的任務呢？ 換句話說，一臺機器無需任何硬編碼規則就能自己學習不同的模式和行為嗎？ 這個問題為新方法鋪平了道路

Machine Learning

機器學習

Machine learning focusses more on learning rules rather than simply executing pre-defined rules. Rules are learnt by exposing the model to relevant examples. For example, in order to understand social sentiment of a product, businesses try to classify online opinions given by their customers into positive or negative. For this task, firstly a set of customer online reviews are manually tagged as positive (denoted by 1) or negative (denoted by 0). These tagged reviews are then input to the model. The model then tries to learn mathematical/statistical rules that enable it to predict the nature of a review (positive or negative) based on its text.

機器學習更多地關注學習規則，而不是簡單地執行預定義的規則。 通過將模型暴露給相關示例來學習規則。 例如，為了理解產品的社會情感，企業試圖將其客戶給出的在線意見分為正面還是負面。 對于此任務，首先將一組客戶在線評論手動標記為正面(由1表示)或負面(由0表示)。 這些標記的評論然后輸入到模型中。 然后，該模型嘗試學習數學/統計規則，以使其能夠根據其文本預測評論的性質(正面或負面)。

Figure 2: Machine Learning uses input data and corresponding answers to learn the rules governing the transformation from data to answers圖2：機器學習使用輸入數據和相應的答案來學習控制從數據到答案的轉換的規則

In order to learn these rules, a ML model needs the following three informations:

為了學習這些規則，ML模型需要以下三個信息：

Data (Input): For a task of sentiment analysis, data includes different textual reviews submitted by the users

數據(輸入)：對于情感分析任務，數據包括用戶提交的不同文本評論

Answers(Output): Each of the reviews in step1, tagged with their sentiments (positive=1, negative=0)

答案(輸出)：步驟1中的每條評論，都標有他們的觀點(正面= 1，負面= 0)

Measure of performance (Loss function): Function which quantifies model performance (loss score) by comparing ‘true answers’ with ‘model predicted answers’. The parameters (weights, bias) are then adjusted in the direction of minimization of loss score. This is the step where the model “learns” the rules based on examples it is exposed to and updates its parameters accordingly. For sentiment analysis task, the loss function is log-sigmoid function.

性能度量(損失函數)：通過將“真實答案”與“模型預測答案”進行比較來量化模型性能(損失得分)的功能。 然后在損失分數最小化的方向上調整參數(權重，偏差)。 這是模型根據其所暴露的示例“學習”規則并相應更新其參數的步驟。 對于情感分析任務，損失函數是對數乙狀結腸函數。

So what does a machine learning model do? It transforms the given ‘data’(input) into meaningful ‘answers’ (output) by learning the rules (optimizing the objective function) through the relevant examples it is exposed to. The term “transforming the data” means representing the data in a form where the task at hand becomes easy to achieve. For example, in figure 3 below, the task is to linearly separate red points from blue. In 2D space (left figure), it is clearly not possible to do so. However, if we transform this data using the rules shown in figure 3(b), the data becomes linearly separable (right figure). The transformation shown in figure 3(b) has facilitated in finding the separating hyperplane.

那么機器學習模型有什么作用？ 通過學習規則(優化目標函數)并通過暴露的相關示例，它將給定的“數據”(輸入)轉換為有意義的“答案”(輸出)。 術語“轉換數據”是指以容易實現手頭的任務的形式表示數據。 例如，在下面的圖3中，任務是線性地將紅色點與藍色分開。 在2D空間(左圖)中，顯然不可能這樣做。 但是，如果我們使用圖3(b)中所示的規則轉換此數據，則數據將變為線性可分離的(右圖)。 圖3(b)所示的變換有助于找到分離的超平面。

Berkeley CS281B Lecture: The Kernel Trick)Berkeley CS281B演講：內核技巧 ) Figure 3(b): Mathematical rules governing the transformation shown in figure 3(a)圖3(b)：控制圖3(a)中所示轉換的數學規則

In conclusion, a ML model ‘searches’ for pertinent representations of the data within a pre-defined space of possibilities (hypothesis space) while being directed by the objective function.

總之，一個ML模型在目標功能的指導下，在可能性的預定義空間(假設空間)內“ 搜索 ”數據的相關表示。

Deep learning

深度學習

Deep learning is a specific form of machine learning where layers of meaningful representations are stacked one after the other. As information passes through each layer, the representation of the input data become more helpful in predicting the output. Each layer can be considered as a filter that purifies the data coming to it so that output becomes increasing clear. The following figure clarifies this process.

深度學習是機器學習的一種特殊形式，其中有意義的表示層一層又一層地堆積在一起。 隨著信息穿過每一層，輸入數據的表示形式在預測輸出中變得更加有用。 每一層都可以看作是過濾器，用于凈化到達其的數據，從而使輸出變得越來越清晰。 下圖闡明了此過程。

Figure 4: Layered representation of a digit classification model (Deep Learning with python; Francois Chollet)圖4：數字分類模型的分層表示(使用Python進行深度學習； Francois Chollet)

The term “deep” in DL is a reference to the presence of successive layers. The depth of a model is equal to the number of successive layers it constitutes. Some ML models use one or two layered representations (shallow networks) whereas modern deep learning models use up to tens or hundreds of layers.

DL中的“深層”一詞是指連續層的存在。 模型的深度等于其構成的連續層數。 一些ML模型使用一層或兩層表示(淺層網絡)，而現代深度學習模型則使用多達數十或數百層。

So how does an iteration of a DL model look like? Flowchart shown in figure 5 depicts the different steps involved in each iteration. Each layer is characterized by weights. Weights can be thought of as projections of input data into higher dimensions. For example, in figure 4, the input image of digit 4 was projected into a 4 dimensional space by layer1. So after data flows through layer 1 we end up with 4 different representations of the image.Once data flows through all of the 4 layers and predicts the output, a loss score is evaluated quantifying the performance of the model. The optimizer then updates the weights in the direction of decreasing loss score. This process is iterated until the loss score reaches a stage where it doesn’t change significantly over iterations.

那么DL模型的迭代看起來如何？ 圖5所示的流程圖描述了每次迭代所涉及的不同步驟。 每層均以重量為特征。 權重可以看作是輸入數據到更高維度的投影。 例如，在圖4中，數字1的輸入圖像被layer1投影到4維空間中。 因此，在數據流過第1層之后，我們最終得到了圖像的4種不同表示形式。一旦數據流過所有4層并預測了輸出，就會對損失評分進行評估，從而量化模型的性能。 然后，優化器會按照降低損失評分的方向更新權重。 反復進行此過程，直到損失分數達到在迭代中不會發生明顯變化的階段為止。

Figure 5: Flowchart representing the steps involved in a ML/DL model圖5：表示ML / DL模型中涉及的步驟的流程圖

Having understood the mechanism around DL models, the next question that arises is that what makes DL better than ML? DL models make problem solving much easier by completely automating “Feature engineering”. ML models needs human intervention in engineering good layers of representation of the input data (e.g., kernel functions in SVM, transformation shown in figure 3(b)). Complex problems require finer representation of input data which cannot be attained manually. DL models, on the other hand, completely automate this step by learning successive layers of data representations (or weights) in one pass. This simplifies the workflow by creating a single end-to-end model where all the features are jointly learnt. In summary, the efficiency of DL models could be attributed to two factors:

了解了DL模型的機制后，出現的下一個問題是，什么使DL優于ML？ DL模型通過完全自動化“特征工程”使解決問題變得更加容易。 ML模型需要人為干預來設計輸入數據表示的良好層(例如，SVM中的內核功能，圖3(b)所示的轉換)。 復雜的問題需要無法手動獲得的輸入數據的更好表示。 另一方面，DL模型通過一次通過學習連續的數據表示層(或權重)來完全自動化此步驟。 通過創建可共同學習所有功能的單個端到端模型，這簡化了工作流程。 總之，DL模型的效率可以歸因于兩個因素：

incremental layer-by-layer mechanism that enables incorporating complex representations of input data and,

漸進的逐層機制，可以合并輸入數據的復雜表示，并且

joint learning of all intermediate layers so that the dependent layers are updated simultaneously.

聯合學習所有中間層，以便同時更新相關層。

結論 (Conclusion)

In this post we covered a brief history of AI and how it evolved over the years through symbolic AI, ML and DL. We also tried to understand how AI, ML and DL are related/correlated with one other (figure 6). These terms often muddle a lot of people and are often used interchangeably.

在這篇文章中，我們簡要介紹了AI的歷史，以及多年來AI通過符號AI，ML和DL演變的過程。 我們還試圖了解AI，ML和DL如何相互關聯/關聯(圖6)。 這些術語經常使很多人感到困惑，并且經?；Q使用。

https://www.edureka.co/blog/ai-vs-machine-learning-vs-deep-learning/)https://www.edureka.co/blog/ai-vs-machine-learning-vs-deep-learning/ )

There is a lot of hype around DL models due to their ability to better deal with complex problems such as image classification, text processing etc. Additionally these models also remove the necessity to manually engineer features, amenable to the objective at hand. Therefore, in the next post we shall be delving into the details of DL models and try to understand its various components along with examples.

由于DL模型能夠更好地處理諸如圖像分類，文本處理等復雜問題，因此它們有很多炒作。此外，這些模型還消除了手動設計功能的必要性，以適應當前的目標。 因此，在下一篇文章中，我們將深入研究DL模型的細節，并嘗試與示例一起理解其各個組成部分。

翻譯自: https://medium.com/@deeptij2007/a-hitchhickers-guide-to-artificial-intelligence-914abdc97359

總結

以上是生活随笔為你收集整理的人工智能的搭便车指南的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。