Shabakadda Neural^{(Neural Networks)} iyo Barashada Qoto dheer^{(Deep Learning)} ayaa hadda ah labada eray ee kulul ee beryahan dambe loo adeegsado sirdoonka macmal ah^{(Artificial Intelligence)} . Horumarkii ugu dambeeyay ee adduunka ee sirdoonka macmalka ah waxaa loo aaneyn karaa labadan maadaama ay door weyn ka qaateen hagaajinta sirdoonka AI.

Eeg hareeraha, oo waxaad ka heli doontaa mashiinno badan oo caqli badan hareeraha. Thanks to Networks Neural^{(Neural Networks)} iyo Barashada qoto dheer^{(Deep Learning)} , shaqooyinka iyo kartida oo markii hore loo tixgeliyey forte ee bini'aadamka ayaa hadda lagu sameeyaa mashiinnada. Maanta, Mashiinnada looma samaynin inay cunaan algorithms-ka adag, laakiin taa beddelkeeda, waxaa la quudiyaa si ay u horumariyaan nidaam iskiis u madaxbannaan, oo awood u leh inay kacaan warshado badan oo ku wareegsan.

Shabakadda Neural^{(Neural Networks)} iyo Barashada Qoto dheer^{(Deep Learning )} waxay siiyeen cilmi-baarayaasha guulo waaweyn oo ay ka mid yihiin aqoonsiga sawirka, aqoonsiga hadalka, helidda xiriir qotodheer oo ku saabsan xogta. Iyada oo lagu taageerayo helitaanka tiro badan oo xog ah iyo awoodda xisaabinta, mashiinadu waxay aqoonsan karaan walxaha, turjumi karaan hadalka, u tababari karaan naftooda si ay u aqoonsadaan qaabab adag, bartaan sida loo dejiyo xeelado iyo samayn karaan qorshayaal kadis ah wakhtiga dhabta ah.

Haddaba, sidee dhab ahaan tani u shaqeysaa? Ma ogtahay in labada Shabakadood ee ^(Networks)Dhexdhexaadka^(Neutral) ah iyo Barashada-Qoto-dheer ay^{(Deep-Learning)} xidhiidh la leeyihiin, dhab ahaantii, si aad u fahamto barasho qoto dheer , waa in aad marka hore fahanto ^(Deep)Shabakadda Neural^{(Neural Networks)} ? Akhri si aad wax badan uga ogaato.

Waa maxay Shabakadda Neural

Shabakadda neerfaha^(Neural) asal ahaan waa qaab barnaamij ama jaantusyo algorithms ah oo awood u siinaya kombuyuutar inuu wax ka barto xogta la eegayo. Shabakadda Neural waxay la mid tahay maskaxda bini'aadamka, taas oo u shaqeysa iyada oo aqoonsanaysa qaababka. Xogta dareenka waxa lagu tarjumaa iyadoo la adeegsanayo garashada mashiinka, calaamadaynta ama ururinta gelinta cayriin. Nidaamyada la aqoonsan yahay waa tirooyin, oo ku xiran vectors, kuwaas oo xogta sida sawirada, codka, qoraalka, iwm. lagu turjumay.

Think Neural Network! Think how a human brain function

Sida kor ku xusan, shabakada neerfaha waxay u shaqeysaa sida maskaxda aadanaha; waxay ku kasbataa aqoonta oo dhan hab waxbarasho. Taas ka dib, miisaannada synaptik waxay kaydiyaan aqoonta la helay. Inta lagu jiro habka waxbarashada, miisaanka synaptik ee shabakada ayaa dib loo habeynayaa si loo gaaro ujeedada la rabo.

Sida maskaxda bini'aadamka, Shabakadaha Neural^{(Neural Networks)} waxay u shaqeeyaan sida nidaamyada xogta-habayn ee aan toos ahayn ee isbarbar socda kuwaas oo si degdeg ah u sameeya xisaabinta sida aqoonsiga qaabka iyo garashada. Natiijadu waxay tahay, shabakadahani waxay si fiican u qabtaan meelaha sida hadalka, maqalka iyo aqoonsiga sawirka halkaasoo agabka/calaamadaha aan toos ahayn.

Erayada fudud, waxaad ku xasuusan kartaa Shabakadda Neural inay tahay shay awood u leh inay kaydiso aqoonta sida maskaxda aadanaha oo aad u isticmaasho si aad u saadaaliso.^{(In simple words, you can remember Neural Network as something which is capable of stocking knowledge like a human brain and use it to make predictions.)}

Qaab dhismeedka Shabakadaha Neural

(Sawirka Xuquuqda: Mathworks)

Shabakadaha^(Networks) Neural waxay ka kooban yihiin saddex lakab,

1. Lakabka galitaanka,
2. Lakabka qarsoon, iyo
3. Lakabka wax soo saarka.

Lakab kastaa wuxuu ka kooban yahay hal ama in ka badan, sida ku cad jaantuska hoose ee goobo yaryar. Xadhkaha u dhexeeya qanjidhada ayaa tilmaamaya qulqulka macluumaadka ee hal nood ilaa kan xiga. Xogtu waxay ka socotaa wax-soo-saarka, ie bidix ilaa midig (mararka qaarkood waxay noqon kartaa midig ilaa bidix ama labadaba).

Noodyada lakabka wax gelinta waa dadban, taasoo la macno ah inaysan wax ka beddelin xogta. Waxay helayaan hal qiime oo ku saabsan wax-soo-galintooda waxayna ku koobiyaan qiimaha wax soo saarkooda badan. Halka^(Whereas) , qanjidhada lakabka qarsoon iyo wax soo saarka ay firfircoon yihiin. Markaa taasi waxay wax ka beddeli karaan xogta.

Qaab dhismeed isku xidhan, qiime kasta oo ka yimaadda lakabka wax gelinta waa la koobiyeeyay oo loo diraa dhammaan qanjidhada qarsoon. Qiimaha gelaya qanjirada qarsoon waxaa lagu dhufto miisaan, tirooyin la sii go'aamiyay oo lagu kaydiyay barnaamijka. Galinta miisaanka leh ayaa markaa lagu daraa si ay u soo saaraan hal lambar. Shabakadaha neerfaha waxay yeelan karaan tiro kasta oo lakabyo ah, iyo tiro kasta oo nood ah lakabkiiba. Codsiyada badankoodu waxay isticmaalaan qaab dhismeedka saddex-lakab ah oo leh ugu badnaan dhowr boqol oo qanjidhada gelinta ah

Tusaalaha Shabakadda Neural^{(Example of Neural Network)}

Tixgeli shabakada neural ee aqoonsan walxaha ku jira signalka sonar-ka, waxaana jira 5000 oo muunado signal ah oo lagu kaydiyay PC-ga. Kombuyuutarku waa inuu caddeeyaa haddii muunadahani ay matalaan bad-hoosaad, nibiriga, barafka, dhagxaanta badda, ama waxbaba? Hababka caadiga ah ee DSP^{(Conventional DSP)} ayaa dhibaatadan ku wajihi doona xisaab iyo algorithms, sida isku xidhka iyo falanqaynta spectrum spectrum.

Iyadoo leh shabakad neural ah, 5000 muunadaha waxaa lagu quudin doonaa lakabka wax soo saarka, taasoo keentay in qiyamku ka soo baxo lakabka wax soo saarka. Doorashada miisaanka saxda ah, wax soo saarka ayaa loo habeyn karaa si ay u soo sheegaan macluumaad ballaaran oo kala duwan. Tusaale ahaan, waxaa laga yaabaa inay jiraan wax soo saaryo loogu talagalay: quusta (haa/maya), dhagaxa badda (haa/maya), nibiriga (haa/maya), iwm.

Miisaannada kale, wax-soo-saarku waxay u kala saari karaan walxaha sida birta ama kuwa aan birta ahayn, noolaha ama aan noolaha ahayn, cadowga ama xulafada, iwm. kaliya xiriirka ka dhexeeya gelinta iyo wax soo saarka ee lagu tilmaamo qiyamka miisaanka la doortay.

Haddaba, aynu fahanno fikradda Barashada qoto dheer.^{(Now, let’s understand the concept of Deep Learning.)}

Waa maxay barasho qoto dheer

Barashada qoto dheer asal ahaan waa qayb ka mid ah shabakadaha Neural^{(Neural Networks)} ; laga yaabee inaad dhihi karto Shabakad Neural^{(Neural Network)} ah oo adag oo lakabyo badan oo qarsoon ay ku dhex jiraan.

Farsamo ahaan, barashada qoto dheer^(Deep) waxa kale oo lagu qeexi karaa inay tahay farsamooyin awood badan oo lagu barto shabakadaha neerfaha. Waxa loola jeedaa shabakadaha neerfaha ee macmalka ah ( ANN ) kuwaas oo ka kooban lakabyo badan, xog ururin ballaaran, qalab kombuyuutar oo awood leh si loo sameeyo qaabka tababarka adag ee suurtogalka ah. Waxay ka kooban tahay fasalka hababka iyo farsamooyinka ka shaqeeya shabakadaha neural ee macmal ah oo leh lakabyo badan oo shaqeyn sii kordheysa.

Qaab dhismeedka shabakada waxbarashada qoto dheer^{(Structure of Deep learning network)}

Shabakado barasho qoto dheer^(Deep) inta badan waxay adeegsadaan qaab-dhismeedka shabakada neerfaha sidaa awgeedna waxaa inta badan lagu tilmaamaa shabakado neerfaha qoto dheer. Isticmaalka shaqada "qoto dheer" waxaa loola jeedaa tirada lakabyada qarsoon ee shabakada neerfaha. Shabakadda neerfaha ee caadiga ah waxay ka kooban tahay saddex lakab oo qarsoon, halka shabakadaha qoto dheer ay yeelan karaan ilaa 120-150.

^(Deep) Barashada ^(Learning)qoto dheer waxay ku lug leedahay quudinta nidaamka kumbuyuutarka xog badan, taas oo ay isticmaali karto si ay go'aan uga gaarto xogta kale. Xogtan waxaa lagu quudiyaa shabakadaha neerfaha, sida kiiska barashada mashiinka. Shabakado barasho qoto dheer^(Deep) ayaa si toos ah xogta uga baran kara sifooyinka iyaga oo aan u baahnayn soo saarista sifada gacanta.

Tusaalooyinka Barashada Qoto dheer^{(Examples of Deep Learning)}

Barashada qoto dheer ayaa hadda laga faa'iidaystaa ku dhawaad ​​warshad kasta oo ka bilaabma Baabuurta^(Automobile) , Aerospace , iyo Automation to Medical . Waa kuwan qaar ka mid ah tusaalooyinka.

• Google , Netflix , iyo Amazon : Google waxay u isticmaashaa codkeeda iyo sawirka aqoonsiga algorithms. Netflix iyo Amazon sidoo kale waxay isticmaalaan barasho qoto dheer si ay u go'aansadaan waxaad rabto inaad daawato ama iibsato xiga
• Wadista darawal la'aan: Cilmi-baarayaashu waxay isticmaalayaan shabakado barasho qoto dheer si ay si toos ah u ogaadaan walxaha sida calaamadaha joogsiga iyo nalalka taraafigga. Barashada qoto dheer^(Deep) waxaa sidoo kale loo isticmaalaa in lagu ogaado dadka lugeynaya, taas oo gacan ka geysaneysa dhimista shilalka.
• Hawada sare iyo Difaaca: Barashada qoto dheer waxaa loo adeegsadaa in lagu garto walxaha laga soo qaado satalaytka ee soo bandhigaya meelaha xiisaha leh, iyo in la aqoonsado meelaha nabdoon ama aan ammaanka ahayn ee ciidamada.
• Thanks to Deep Learning , Facebook si toos ah u helo oo calaamad u saaxiibada ee sawiradaada. Skype waxay tarjumi kartaa isgaarsiinta lagu hadlo waqtiga dhabta ah iyo sidoo kale si sax ah.
• Cilmi-baaris caafimaad: Cilmi-baarayaasha caafimaadku waxay isticmaalayaan barasho qoto dheer si ay si toos ah u ogaadaan unugyada kansarka
• Automation Warshadaha^{(Industrial Automation)} : Barashada qoto dheer waxay gacan ka geysaneysaa hagaajinta badbaadada shaqaalaha ee agagaarka mishiinada culus iyadoo si toos ah loo ogaanayo marka dadka ama walxuhu ay ku jiraan masaafo ammaan darro ah oo mashiinada ah.
• Elektroonik: Barashada qoto dheer^(Deep) waxaa loo istcimaalay tarjumaada maqalka iyo hadalka tooska ah.

Akhriso^(Read) : Waa maxay Barashada Mashiinka iyo Barashada Qoto dheer^{(Machine Learning and Deep Learning)} ?

Gabagabo^(Conclusion)

Fikradda Shabakadda Neural^{(Neural Networks)} maaha mid cusub, cilmi-baarayaashuna waxay la kulmeen guul dhexdhexaad ah tobankii sano ee la soo dhaafay ama wax ka badan. Laakin ciyaarta dhabta ah ee wax ka beddesha waxay ahayd horumarka shabakadaha neerfaha ee Deep .

Iyada oo la fulinayo hababka barashada mashiinka dhaqameed waxay muujisay in shabakadaha neerfaha qoto dheer la tababari karo oo la tijaabin karo maaha kaliya cilmi-baarayaal yar, laakiin waxay leedahay baaxadda in ay qaataan shirkadaha tiknoolajiyada caalamiga ah si ay ula yimaadaan hal-abuuro wanaagsan mustaqbalka dhow.

Thanks to Deep Learning and Neural Network, AI is not just doing the tasks, but it has started to think!

What is Deep Learning and Neural Network

Neural Networks and Deep Learning are currently the two hot buzzwords that are being used nowadays with Artificial Intelligence. The recent developments in the world of Artificial intelligence can be attributed to these two as they have played a significant role in improving the intelligence of AI.

Look around, and you will find more and more intelligent machines around. Thanks to Neural Networks and Deep Learning, jobs and capabilities that were once considered the forte of humans are now being performed by machines. Today, Machines are no longer made to eat more complex algorithms, but instead, they are fed to develop into an autonomous, self-teaching system capable of revolutionizing many industries all around.

Neural Networks and Deep Learning have lent enormous success to the researchers in tasks such as image recognition, speech recognition, finding deeper relations in a data sets. Aided by the availability of massive amounts of data and computational power, machines can recognize objects, translate speech, train themselves to identify complex patterns, learn how to devise strategies and make contingency plans in real-time.

So, how exactly does this work? Do you know that both Neutral Networks and Deep-Learning related, in fact, to understand Deep learning, you must first understand about Neural Networks? Read on to know more.

What is a Neural Network

A Neural network is basically a programming pattern or a set of algorithms that enables a computer to learn from the observational data. A Neural network is similar to a human brain, which works by recognizing the patterns. The sensory data is interpreted using a machine perception, labeling or clustering raw input. The patterns recognized are numerical, enclosed in vectors, into which the data such are images, sound, text, etc. are translated.

Think Neural Network! Think how a human brain function

As mentioned above, a neural network functions just like a human brain; it acquires all the knowledge through a learning process. After that, synaptic weights store the acquired knowledge. During the learning process, the synaptic weights of the network are reformed to achieve the desired objective.

Just like the human brain, Neural Networks work like non-linear parallel information-processing systems which rapidly perform computations such as pattern recognition and perception. As a result, these networks perform very well in areas like speech, audio and image recognition where the inputs/signals are inherently nonlinear.

In simple words, you can remember Neural Network as something which is capable of stocking knowledge like a human brain and use it to make predictions.

Structure of Neural Networks

(Image Credit: Mathworks)

Neural Networks comprises of three layers,

1. Input layer,
2. Hidden layer, and
3. Output layer.

Each layer consists of one or more nodes, as shown in the below diagram by small circles. The lines between the nodes indicate the flow of information from one node to the next. The information flows from the input to the output, i.e. from left to right (in some cases it may be from right to left or both ways).

The nodes of the input layer are passive, meaning they do not modify the data. They receive a single value on their input and duplicate the value to their multiple outputs. Whereas, the nodes of the hidden and output layer are active. Thus that can they modify the data.

In an interconnected structure, each value from the input layer is duplicated and sent to all of the hidden nodes. The values entering a hidden node are multiplied by weights, a set of predetermined numbers stored in the program. The weighted inputs are then added to produce a single number. Neural networks can have any number of layers, and any number of nodes per layer. Most applications use the three-layer structure with a maximum of a few hundred input nodes

Example of Neural Network

Consider a neural network recognizing objects in a sonar signal, and there are 5000 signal samples stored in the PC. The PC has to figure out if these samples represent a submarine, whale, iceberg, sea rocks, or nothing at all? Conventional DSP methods would approach this problem with mathematics and algorithms, such as correlation and frequency spectrum analysis.

While with a neural network, the 5000 samples would be fed to the input layer, resulting in values popping from the output layer. By selecting the proper weights, the output can be configured to report a wide range of information. For instance, there might be outputs for: submarine (yes/no), sea rock (yes/no), whale (yes/no), etc.

With other weights, the outputs can classify the objects as metal or non-metal, biological or non-biological, enemy or ally, etc. No algorithms, no rules, no procedures; only a relationship between the input and output dictated by the values of the weights selected.

Now, let’s understand the concept of Deep Learning.

What is a Deep Learning

Deep learning is basically a subset of Neural Networks; perhaps you can say a complex Neural Network with many hidden layers in it.

Technically speaking, Deep learning can also be defined as a powerful set of techniques for learning in neural networks. It refers to artificial neural networks (ANN) that are composed of many layers, massive data sets, powerful computer hardware to make complicated training model possible. It contains the class of methods and techniques that employ artificial neural networks with multiple layers of increasingly richer functionality.

Structure of Deep learning network

Deep learning networks mostly use neural network architectures and hence are often referred to as deep neural networks. Use of work “deep” refers to the number of hidden layers in the neural network. A conventional neural network contains three hidden layers, while deep networks can have as many as 120- 150.

Deep Learning involves feeding a computer system a lot of data, which it can use to make decisions about other data. This data is fed through neural networks, as is the case in machine learning. Deep learning networks can learn features directly from the data without the need for manual feature extraction.

Examples of Deep Learning

Deep learning is currently being utilized in almost every industry starting from Automobile, Aerospace, and Automation to Medical. Here are some of the examples.

• Google, Netflix, and Amazon: Google uses it in its voice and image recognition algorithms. Netflix and Amazon also use deep learning to decide what you want to watch or buy next
• Driving without a driver: Researchers are utilizing deep learning networks to automatically detect objects such as stop signs and traffic lights. Deep learning is also used to detect pedestrians, which helps decrease accidents.
• Aerospace and Defense: Deep learning is used to identify objects from satellites that locate areas of interest, and identify safe or unsafe zones for troops.
• Thanks to Deep Learning, Facebook automatically finds and tags friends in your photos. Skype can translate spoken communications in real-time and pretty accurately too.
• Medical Research: Medical researchers are using deep learning to automatically detect cancer cells
• Industrial Automation: Deep learning is helping to improve worker safety around heavy machinery by automatically detecting when people or objects are within an unsafe distance of machines.
• Electronics: Deep learning is being used in automated hearing and speech translation.

Read: What is Machine Learning and Deep Learning?

Conclusion

The concept of Neural Networks is not new, and researchers have met with moderate success in the last decade or so. But the real game-changer has been the evolution of Deep neural networks.

By out-performing the traditional machine learning approaches it has showcased that deep neural networks can be trained and trialed not just by few researchers, but it has the scope to be adopted by multinational technology companies to come with better innovations in the near future.

Thanks to Deep Learning and Neural Network, AI is not just doing the tasks, but it has started to think!

Related posts

• Qabanqaabiyaha SMS: Codsiga SMS waxa ku shaqeeya Barashada Mashiinka

• Waa maxay Barashada Mashiinka iyo Barashada Qoto dheer ee Sirdoonka Artificial

• Sida loo rakibo Drupal adoo isticmaalaya WAMP Windows

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

• Ku samee Xarunta Raadiyaha Internetka oo bilaash ah Windows PC

• Miisaska Laptop-ka ee ugu Wanaagsan ee lagu iibsado onlayn

• Sida loo isticmaalo Template si loogu sameeyo dukumeenti LibreOffice

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

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

• Tilmaamaha ugu fiican ee LibreOffice Calc

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

• Sida erayga sirta ah loogu ilaaliyo oo loo ilaaliyo dukumeenti PDF LibreOffice

• 10ka Laambadood ee ugu fiican ee USB-ga ee Laptop-yada

• Sida loo tirtiro Koontadaada LastPass

• Sidee loo Xidhaa Koontadaada Payoneer?

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

• Dhaqanka shirarka fiidyaha, talooyin iyo xeerar aad u baahan tahay inaad raacdo

• Sagaal Nostalgic Tech dhawaqyada malaha aadan maqlin sanado

• Boorsooyinka Laabtoobka ugu Fiican ee Ragga iyo Dumarka

• Cyber ​​​​Isniinta & Jimcaha Madoow Tilmaamaha wax iibsiga ee aad rabto inaad raacdo