Aaladaha ku xiran intarneedka^(Internet) waxaa loo yaqaannaa aaladaha casriga ah. Wax kasta oo la xiriira internetka^(Internet) waxaa loo yaqaan aaladda smart^{(smart device)} . Xaaladdan oo kale, koodka ka dhigaya aaladaha SMARTER - si ay ugu shaqeyso ugu yaraan ama iyada oo aan wax faragelin bini'aadam ahi jirin - waxaa la odhan karaa waxay ku saleysan tahay Sirdoonka Artificial^{(Artificial Intelligence)} (AI). Labada kale, oo kala ah: Barashada Mashiinka^{(Machine Learning)} (ML), iyo Barashada Deep^{(Deep Learning)} (DL), waa noocyo kala duwan oo algorithms ah oo loo dhisay inay awoodo badan u keenaan aaladaha casriga ah. Aynu si faahfaahsan hoos u aragno AI vs ML vs DL si aan u fahanno waxay qabtaan iyo sida ay ugu xidhan yihiin AI.

Waa maxay sirdoonka Artificial marka la eego ML & DL

AI waxaa loogu yeeri karaa habka ugu sarreeya ee Mashiinka Learning^{(Machine Learning)} (ML), iyo hababka Barashada qoto dheer^{(Deep Learning)} (DL). AI inta badan waa dallad loo isticmaalo ML iyo DL. Barashada qoto dheer^{(Deep Learning)} waa mar kale, qayb ka mid ah Barashada Mashiinka^{(Machine Learning)} (fiiri sawirka kore).

Qaar ayaa ku doodaya in Barashada Mashiinku^{(Machine Learning)} aanay ahayn qayb ka mid ah AI caalamiga ah. Waxay yiraahdeen ML waa cilmi dhammaystiran oo iskii u gaar ah, sidaas darteed, looma baahna in loogu yeero iyada oo la tixraacayo Sirdoonka Artificial^{(Artificial Intelligence)} . AI waxay ku horumartaa xogta: Xogta Weyn^{(Big Data)} . Xogta badan ee ay isticmaasho, waa inta saxda ah. Ma aha in ay had iyo jeer si sax ah u saadaaliso. Waxaa sidoo kale jiri doona calan been abuur ah. AI waxay isku tababartaa khaladaadkan waxayna ku fiicnaan doontaa waxa ay tahay inay qabato - iyada oo leh ama la'aanteed kormeerka aadanaha.

Sirdoonka macmalka ah si sax ah looma qeexi karo maadaama uu galay ku dhawaad ​​dhammaan warshadaha oo uu saameeyay noocyo badan oo habraacyo (ganacsi) iyo algorithms. Waxaan dhihi karnaa in Sirdoonka^{(Intelligence)} Artificial uu ku saleysan yahay Sayniska Xogta^{(Data Science)} (DS: Big Data ) oo uu ka kooban yahay Barashada Mashiinka^{(Machine Learning)} oo ah qaybteeda gaarka ah. Sidoo kale^(Likewise) , Barashada Qoto dheer^{(Deep Learning)} waa qayb gaar ah oo ka mid ah Barashada Mashiinka^{(Machine Learning)} .

Habka suuqa IT-gu u janjeero, mustaqbalka waxaa lagu xakameyn doonaa aaladaha smart ee ku xiran, oo loo yaqaan ' Internet of Things' (IoT) . Aaladaha casriga^(Smart) ah waxa loola jeedaa garaadka macmal: si toos ah ama si dadban. Waxaad horeba u isticmaalaysay sirdoonka macmal (AI) hawlo badan oo nolol maalmeedkaaga ah. Tusaale ahaan, ku qorida kiiboodhka casriga ee casriga ah kaas oo ku sii wanaajinaya "soo jeedinta erayada". Tusaalooyinka kale ee aad ogaan la'aan tahay inaad la macaamilayso Sirdoonka Artificial^{(Artificial Intelligence)} waxay ka raadineysaa waxyaabo ku jira internetka^(Internet) , wax iibsiga online, iyo dabcan, Gmail - ka iyo sanduuqyada^(Outlook) emailka ee weligeed ah ee caqli-gal ah.

Waa maxay Barashada Mashiinka

Barashada^(Learning) Mashiinku waa goob sirdoonka macmal ah^{(Artificial Intelligence)} halkaas oo ujeedadu tahay in la sameeyo mishiinka (ama kombuyuutar, ama software) wax barto oo iskiis u tababaro iyada oo aan wax barnaamijyo badan la samayn. Aaladaha noocan oo kale ah waxay u baahan yihiin barnaamijyo yar marka ay dabaqaan hababka aadanaha si ay u dhamaystiraan hawlaha, oo ay ku jiraan barashada sida si fiican loo qabto. Asal ahaan^(Basically) , ML macnaheedu waa in yar oo kombuyuutar/qalab/software la program-gareeyo oo loo ogolaado in uu iskii u barto.

Waxaa jira dhowr hab oo lagu fududeeyo Barashada Mashiinka^{(Machine Learning)} . Kuwaas, saddexdan soo socda ayaa si weyn loo isticmaalaa:

1. La kormeero,
2. Ilaalin la'aan, iyo
3. xoojinta barashada.

Barashada Mashiinka Barashada La Ilaaliyo^{(Machine Learning)}

Waxaa lagu kormeeraa dareenka ah in programmer-yadu ay marka hore mishiinka siiyaan xog calaamadaysan iyo jawaabo hore loo habeeyey. Halkan, calaamaduhu waxay ka dhigan yihiin magacyada safka ama tiirka ee kaydka xogta ama xaashida xaashida. Ka dib markii ay quudiyaan qaybo badan oo xogtan ah kombuyuutarka, waxay diyaar u tahay inay falanqeyso xog dheeraad ah oo ay bixiso natiijooyinka keligiis. Taas macneheedu waxa weeye waxaad baray kumbiyuutarka sida loo falanqeeyo xogta la siiyo.

Caadi ahaan, waxaa lagu xaqiijiyaa iyadoo la adeegsanayo qaanuunka 80/20. Qaybo^(Huge) badan oo xog ah ayaa lagu quudiyaa kombuyuutar kaas oo tijaabiya oo baranaya macquulka ka dambeeya jawaabaha. Boqolkiiba 80 xogta dhacdada waxaa la siiyaa kombayuutarka oo ay la socoto jawaabo. Boqolkiiba 20 ka soo hadhay ayaa la quudiyaa iyada oo aan jawaabo la helin si loo eego in kombuyuutarku la iman karo natiijooyin habboon. Boqolkiiba 20-kan waxa loo istcimaalayaa hubinta iskutallaabta si loo arko sida kombayuutarku (mashiinku) u baranayo.

Barashada Mashiinka Aan La Ilaalin Lahayn

Barashada aan la kormeerin waxay dhacdaa marka mishiinka lagu quudiyo xogta xogta aan sugnayn ee aan la calaamadin, oo aan nidaamsaneyn. Mashiinku waa inuu ogaadaa sida loo soo saaro natiijooyinka. Tusaale ahaan, haddii aad bixiso kubbado jilicsan oo midabyo kala duwan leh, waa inay awood u leedahay inay u kala soocdo midabyo. Sidaa darteed, mustaqbalka, marka mishiinka lagu soo bandhigo kubbadda jilicsan ee cusub, waxay aqoonsan kartaa kubbadda calamadaha hadda jira ee kaydkeeda. Habkan ma jiro xog tababar. Mashiinku waa inuu iskii u barto.

Xoojinta Waxbarashada

Mashiinnada samayn kara isku xigxiga go'aannada waxay ku dhacaan qaybtan. Markaa waxaa jira nidaam abaal-marineed. Haddii mashiinku uu ku fiican yahay wax kasta oo barnaamij-sameeyaha uu rabo, waxay helaysaa abaalmarin. Mashiinka waxaa loo habeeyey hab uu u rabo abaalmarinta ugu badan. Si loo helo, waxay xallisaa dhibaatooyinka iyadoo la samaynayo algorithms kala duwan xaalado kala duwan. Taas macnaheedu waa kombuyuutarka AI wuxuu isticmaalaa habab tijaabo iyo khalad ah si uu u keeno natiijooyin.

Tusaale ahaan, haddii mishiinku yahay baabuur is-wada, waa inuu abuuraa muuqaalkiisa waddada. Ma jirto hab uu barnaamij-sameeyaha u barnaamiji karo tillaabo kasta maadaama isaga ama iyadu aanay ka fikiri karin dhammaan suurtogalnimada marka mishiinku ku jiro waddada. Taasi waa halka ay ka timaado Waxbarashada Xoojinta^{(Reinforcement Learning)} . Waxa kale oo aad wici kartaa tijaabo iyo khalad AI.

Sidee Barashada Qoto dheer uga duwan tahay Barashada Mashiinka^{(Machine Learning)}

Barashada qoto dheer^{(Deep Learning)} waxaa loogu talagalay hawlo aad u adag. Barashada qoto dheer^{(Deep Learning)} waa qayb ka mid ah Barashada Mashiinka^{(Machine Learning)} . Kaliya in ay ka kooban tahay shabakado neerfaha oo ka caawiya mashiinka waxbarashada. Shabakadaha^(Manmade) neerfaha ee dadku sameeyeen maaha kuwo cusub. Shaybaadhka^(Labs) adduunka oo dhan ayaa isku dayaya inay dhisaan oo hagaajiyaan shabakadaha neerfaha si ay mashiinadu u gaaraan go'aano xog ogaal ah. Waa inaad maqashay Sophia , oo ah nin bini'aadanti ah oo ku sugan Sucuudiga^(Saudi) oo la siiyay dhalasho joogto ah. Shabakadaha neerfaha ayaa la mid ah maskaxda bini'aadamka laakiin maaha kuwo u casrisan sida maskaxda oo kale.

Waxaa jira shabakado wanaagsan oo bixiya barasho qoto dheer oo aan la ilaalin. Waxaad dhihi kartaa in Barashada qoto dheer^{(Deep Learning)} ay tahay shabakado neerfaha badan oo ku dayanaya maskaxda aadanaha. Weli, iyada oo la haysto xog muunad ku filan, algorithms-yada Barashada Deep^{(Deep Learning)} waxaa loo isticmaali karaa in laga soo qaado tafaasiisha xogta muunada. Tusaale ahaan, mashiinka sawirka ee mashiinka DL, way fududahay in la abuuro wejiyada bini'aadamka oo leh shucuur isbeddelaya iyadoo loo eegayo su'aalaha mashiinka la waydiiyo.

Midka kore wuxuu ku sharxayaa AI vs MI vs DL luqad fudud. AI iyo ML waa beero ballaaran - kuwaas oo hadda furmaya oo leh awood aad u weyn. Tani waa sababta dadka qaar ay uga soo horjeedaan isticmaalka Mashiinka Learning^{(Machine Learning)} iyo Barashada qoto dheer^{(Deep Learning)} ee sirdoonka macmal ah^{(Artificial Intelligence)} .

What are Machine Learning and Deep Learning in Artificial Intelligence

Devices connected to the Internet are called smart devicеs. Pretty much еνerуthing related to the Internet is known as a smart device. In this context, the code that makes the devices SMARTER – so that it can work with minimal or without any human intervention – can be said to be based on Artificial Intelligence (AI). The other two, namely: Machine Learning (ML), and Deep Learning (DL), are different types of algorithms built to bring more capabilities to the smart devices. Let’s see AI vs ML vs DL in detail below to understand what they do and how they are connected to AI.

What is Artificial Intelligence with respect to ML & DL

AI can be called a superset of Machine Learning (ML) processes, and Deep Learning (DL) processes. AI usually is an umbrella term that is used for ML and DL. Deep Learning is again, a subset of Machine Learning (see image above).

Some argue that Machine Learning is no more a part of the universal AI. They say ML is a complete science in its own right and thus, need not be called with reference to Artificial Intelligence. AI thrives on data: Big Data. The more data it consumes, the more accurate it is. It is not that it will always predict correctly. There will be false flags as well. The AI trains itself on these mistakes and becomes better at what it is supposed to do – with or without human supervision.

Artificial Intelligence cannot be defined properly as it has penetrated into almost all industries and affects way too many types of (business) processes and algorithms. We can say that Artificial Intelligence is based on Data Science (DS: Big Data) and contains Machine Learning as its distinct part. Likewise, Deep Learning is a distinct part of Machine Learning.

The way the IT market is tilting, the future would be dominated with connected smart devices, called the Internet of Things (IoT). Smart devices mean artificial intelligence: directly or indirectly. You are already using artificial intelligence (AI) in many tasks in your daily life. For example, typing on a smartphone keyboard that keeps on getting better on “words suggestion”. Among other examples where you unknowingly are dealing with Artificial Intelligence are searching for things on the Internet, online shopping, and of course, the ever-smart Gmail and Outlook email inboxes.

What is Machine Learning

Machine Learning is a field of Artificial Intelligence where the aim is to make a machine (or computer, or a software) learn and train itself without much programming. Such devices need less programming as they apply human methods to complete tasks, including learning how to perform better. Basically, ML means programming a computer/device/software a bit and allowing it to learn on its own.

There are several methods to facilitate Machine Learning. Of them, the following three are used extensively:

1. Supervised,
2. Unsupervised, and
3. Reinforcement learning.

Supervised Learning in Machine Learning

Supervised in a sense that programmers first provide the machine with labeled data and already processed answers. Here, labels mean the row or column names in a database or spreadsheet. After feeding huge sets of such data to the computer, it is ready to analyze further data sets and provide results on its own. That means you taught the computer how to analyze the data fed to it.

Usually, it is confirmed using the 80/20 rule. Huge sets of data are fed to a computer that tries and learns the logic behind the answers. 80 percent of data from an event is fed to the computer along with answers. The remaining 20 percent is fed without answers to see if the computer can come up with proper results. This 20 percent is used for cross-checking to see how the computer (machine) is learning.

Unsupervised Machine Learning

Unsupervised Learning happens when the machine is fed with random data sets that are not labeled, and not in order. The machine has to figure out how to produce the results. For example, if you offer it softballs of different colors, it should be able to categorize by colors. Thus, in the future, when the machine is presented with a new softball, it can identify the ball with already present labels in its database. There is no training data in this method. The machine has to learn on its own.

Reinforcement Learning

Machines that can make a sequence of decisions fall into this category. Then there is a reward system. If the machine does good at whatever the programmer wants, it gets a reward. The machine is programmed in a way that it craves maximum rewards. And to get it, it solves problems by devising different algorithms in different cases. That means the AI computer uses trial and error methods to come up with results.

For example, if the machine is a self-driving vehicle, it has to create its own scenarios on road. There is no way a programmer can program every step as he or she can’t think of all the possibilities when the machine is on the road. That is where Reinforcement Learning comes in. You can also call it trial and error AI.

How is Deep Learning different from Machine Learning

Deep Learning is for more complicated tasks. Deep Learning is a subset of Machine Learning. Only that it contains more neural networks that help the machine in learning. Manmade neural networks are not new. Labs across the world are trying to build and improve neural networks so that the machines can make informed decisions. You must have heard of Sophia, a humanoid in Saudi that was provided regular citizenship. Neural networks are like human brains but not as sophisticated as the brain.

There are some good networks that provide for unsupervised deep learning. You can say that Deep Learning is more neural networks that imitate the human brain. Still, with enough sample data, the Deep Learning algorithms can be used to pick up details from sample data. For example, with an image processor DL machine, it is easier to create human faces with emotions changing according to the questions the machine is asked.

The above explains AI vs MI vs DL in easier language. AI and ML are vast fields – that are just opening up and have tremendous potential. This is the reason some people are against using Machine Learning and Deep Learning in Artificial Intelligence.

Related posts

• Qabanqaabiyaha SMS: Codsiga SMS waxa ku shaqeeya Barashada Mashiinka

• Xaqiiqooyin, Khuraafaad, Dood ku saabsan Sirdoonka Artificial

• Waa maxay Learning Deep iyo Network Neural

• Software-ka ugu Wacan ee Sirdoonka Artificial Free ee Windows 10

• Sida loo rakibo Drupal adoo isticmaalaya WAMP Windows

• Ugu Fiican Software & Hardware Seeraar boorsada Windows, iOS, Android

• Automate.io waa qalab otomaatig ah oo bilaash ah iyo beddelka IFTTT

• Barnaamijyada OpenGL kuma shaqeeyaan bandhiga wireless-ka ee Miracast Windows 11/10

• Boorsooyinka Laabtoobka ugu Fiican ee Ragga iyo Dumarka

• Talooyin, Qalab & Adeegyo Maareynta Sumcada ee khadka tooska ah

• Khalad ayaa dhacay markii la hubinayay wixii ku soo cusboonaadey VLC

• Whiteboard Fox waa sabuur cad oo bilaash ah oo khadka tooska ah kaas oo u oggolaanaya wadaagista waqtiga dhabta ah

• Qalabka ugu fiican ee SMS-ka looga soo diro bilaash

• Disqus sanduuqa faallooyinka oo aan soo dejinaynin ama muujinaynin mareegaha

• Ku samee Xarunta Raadiyaha Internetka oo bilaash ah Windows PC

• Sida loo Beddelka Binary-ga Qoraal ahaan Isticmaalka Qoraalkan una beddelo Binary

• App-ka fariimaha kullanku waxa uu bixiyaa ammaan xooggan; Lambar telefoon looma baahna!

• Waa maxay macnaha NFT iyo Sidee loo abuuraa NFT Digital Art?

• Sagaal Nostalgic Tech dhawaqyada malaha aadan maqlin sanado

• Waa maxay Ciyaarta Dare ee nibiriga buluuga ah