機器視覺在深學(xué)習(xí)神經(jīng)網(wǎng)絡(luò)中的應(yīng)用

　　人工智能（AI）長期以來一直是科幻小說作家和學(xué)者的主題。將人腦的復(fù)雜性復(fù)制到計算機中的挑戰(zhàn)催生了新一代的科學(xué)家、數(shù)學(xué)家和計算機算法開發(fā)人員。持續(xù)的研究已經(jīng)讓位給使用人工智能，更經(jīng)常被稱為深學(xué)習(xí)或機器學(xué)習(xí)，越來越多的應(yīng)用程序的一部分，我們的世界。雖然基本概念已經(jīng)存在了很長一段時間，商業(yè)現(xiàn)實從來沒有完全實現(xiàn)。在最近幾年中，數(shù)據(jù)生成的速度急劇上升，開發(fā)者不得不思考如何編寫算法來從中提取有價值的數(shù)據(jù)和統(tǒng)計數(shù)據(jù)。此外，另一個關(guān)鍵因素是高可用性的計算資源水平，云已經(jīng)心甘情愿地取得了。例如，在你的口袋里的智能手機可能會使用谷歌的現(xiàn)在（好谷歌）或蘋果的Siri語音命令的應(yīng)用程序，使用深度學(xué)習(xí)算法的功率，稱為（人工）神經(jīng)網(wǎng)絡(luò)，使語音識別和學(xué)習(xí)能力。然而，除了與你的電話交談的樂趣和方便，有一系列的工業(yè)，汽車和商業(yè)應(yīng)用，現(xiàn)在受益于深學(xué)習(xí)神經(jīng)網(wǎng)絡(luò)的力量。

　　The convolutional neural network

　　Before taking a look at some of those applications， let’s investigate how a neural network works and what resources it needs. When we talk generally about neural networks we should more accurately describe them as artificial neural networks. Implemented as software algorithms， they are based on the biological neural networks – the central nervous system – of humans and animals. There have been several different types of neural network architecture conceived over the years of which the convolutional neural network （CNN） has been the most widely adopted. One of the key reasons for this has been that their architectural approach makes them well suited for using the parallelization techniques offered by hardware accelerators based around GPU and FPGA devices. Another reason for the popularity of CNNs is that they suit working with data that has a lot of spatial continuity， of which image processing applications are a perfect fit. Spatial continuity refers to pixels in the vicinity of a specific location sharing similar intensity and color attributes. CNNs are architected out of different layers， each having a specific purpose， and there are two distinct phases used in their operation. The first part is an instruction， or training phase that allows the processing algorithm to understand what data it has and the relationship， or context between each piece of data. The CNN is created as a learning framework from the structured and unstructured data， with computer created neurons forming the network of connections and breaks. Pattern matching is a key concept behind a CNN， something that is used extensively in machine learning.