Today, artificial intelligence helps doctors diagnose patients, pilots fly commercial aircraft, and city planners predict traffic. But no matter what these AIs are doing, the computer scientists who designed them likely don’t know exactly how they’re doing it. This is because artificial intelligence is often self-taught, working off a simple set of instructions to create a unique array of rules and strategies. So how exactly does a machine learn?
Bugun sun’iy intellekt shifokorlarga tashxis qo’yishda yordam bermoqda, pilotlarga samolyot boshqarishda, muhandis -larga tirbandliklarni prognoz qilishda. Lekin SI nima qilishidan qat’iy nazar, uni ishlab chiqqan dasturchilar katta ehtimol bilan qanday qilayotganini bilmaydilar. Buning sababi ko’p hollarda SI o’zi o’rgangan, oddiygina qo’llanmalar to’plamidan o’zgacha qoida va strategiyalar yaratadi. Xo’sh aynan qanday qilib mashina o’rganadi?
There are many different ways to build self-teaching programs. But they all rely on the three basic types of machine learning: unsupervised learning, supervised learning, and reinforcement learning. To see these in action, let’s imagine researchers are trying to pull information from a set of medical data containing thousands of patient profiles.
O’zi o’rganadigan programmalar yaratishning ko’p yo’llari bor. Lekin ularning barchasi uch asosiy mashina o’rganuvchi sistemaga asoslanadi: nazoratsiz o’rganish, nazoratli o’rganish va mustahkam o’rganish. Bularni hayotda ko’rish uchun, tadqiqotchilarni minglab bemorlar tibbiy ma’lumotlari orasidan informatsiya olishini tasavvur qilaylik.
First up, unsupervised learning. This approach would be ideal for analyzing all the profiles to find general similarities and useful patterns. Maybe certain patients have similar disease presentations, or perhaps a treatment produces specific sets of side effects. This broad pattern-seeking approach can be used to identify similarities between patient profiles and find emerging patterns, all without human guidance.
Birinchi o’rinda, nazoratsiz o’rganish. Bu usul hamma profillarni umumiy o’xshashlik va foydali yo’llarni topish uchun idealdir. Balkim ba’zi bemorlarda o’xshash kasallik belgilar bor yoki ehtimol davolanishning ba’zi nuqsonlari bo’ladi. Bu keng yo’l topuvchi usul inson aralashuvisiz bemorlarning ma’lumotlaridan o’xshashlikni topishda ishlatish mumkin.
But let's imagine doctors are looking for something more specific. These physicians want to create an algorithm for diagnosing a particular condition. They begin by collecting two sets of data— medical images and test results from both healthy patients and those diagnosed with the condition. Then, they input this data into a program designed to identify features shared by the sick patients but not the healthy patients. Based on how frequently it sees certain features, the program will assign values to those features’ diagnostic significance, generating an algorithm for diagnosing future patients. However, unlike unsupervised learning, doctors and computer scientists have an active role in what happens next. Doctors will make the final diagnosis and check the accuracy of the algorithm’s prediction. Then computer scientists can use the updated datasets to adjust the program’s parameters and improve its accuracy. This hands-on approach is called supervised learning.
Lekin tasavvur qiling shifokorlar aniqroq narsani izlashmoqda. Bu shifokorlar ma’lum bir kasallikka tashxis qo’yish uchun algoritm yaratsishmoqchi. Ular 2 to’plam ma’lumotlarni yig’ishdan boshlashadi-- ikkala sog’ bemorlar va kasallikka chalingan bemorlardan tibbiy rasmlar va test natijalarini olishadi. So’ng, bu ma’lumotlarni kasal bemorlarning xususiyatlarini aniqlash uchun dasturga kirg’iziladi lekin sog’ bemorlarniki emas. Ma’lum xususiyatlarni qanchalik tez uchratishiga qarab, dastur har bir xususiyatning muhimligiga qarab diagnostik qymat berib chiqadi, va bemorlarga tashxis qo’yuvchi algoritm ishlab chiqaradi. Ammo, boshqaruvsiz o’rganishdan farqli ravishda, shifokor va dasturchilar keyingi jarayonda faol rol o’ynaydilar. Shifokorlar oxirgi tashxisni qo’yadilar va algoritm natijasining aniqligini tekshiradilar. Dasturchilar yangi ma’lumotlarni dastur paramaterlarini to’g’irlash va aniqligini yaxshilash uchun ishlatishlari Bu amaliy usul boshqaruvsiz o’rganish deyiladi.
Now, let’s say these doctors want to design another algorithm to recommend treatment plans. Since these plans will be implemented in stages, and they may change depending on each individual's response to treatments, the doctors decide to use reinforcement learning. This program uses an iterative approach to gather feedback about which medications, dosages and treatments are most effective. Then, it compares that data against each patient’s profile to create their unique, optimal treatment plan. As the treatments progress and the program receives more feedback, it can constantly update the plan for each patient. None of these three techniques are inherently smarter than any other. While some require more or less human intervention, they all have their own strengths and weaknesses which makes them best suited for certain tasks. However, by using them together, researchers can build complex AI systems, where individual programs can supervise and teach each other. For example, when our unsupervised learning program finds groups of patients that are similar, it could send that data to a connected supervised learning program. That program could then incorporate this information into its predictions. Or perhaps dozens of reinforcement learning programs might simulate potential patient outcomes to collect feedback about different treatment plans.
Endi, ayataylik shifokorlar boshqa davolash rejasi algoritm tuzmoqchilar. Bu rejalar qadamma-qadam borar ekan va har bir bemorning holatiga qarab o’zgarar ekan, shifokorlar mustahkamlovchi o’rganishni ishlatishga qaror qilganlar. Bu dastur takroriy usulni qaysi dori va davolash eng optimali ekanligini aniqlashda feedbek to’playdi. Keyin, har bir bemor bilan optimal bo’lgan davolash rejasini tuzish uchun solishtirib chiqadi. Davolash davom etar va dastur feedback olar ekan, u doimiy tarzda har bir bemor rejasini yangilab boradi. Hech qaysi uch usul bir-biridan kelib chiqishi jihatidan aqlliroq emas. Ba’zilari ko’proq yo kamroq inson aralashuvini qilsa-da, barchasini ma’lum ishga mos qiladigan kuchli va kuchsiz jihatlari bor. Lekin, ularni birga ishlatib, tadqiqotchilar mukammal ma’lum dasturlar, bir-birini nazorat qiladigan va o’rgatadigan SI sistemalar yarata oladilar. Misol uchun, boshqaruvsiz o’rganadigan dastur o’xshash bemorlarni guruhini topsa, buni ulangan boshqaruvli o’rganish dasturiga yuboradi. U dastur keyin bu ma’lumotni bashoratga aylantira oladi Yoki ehtimol ko’plab majburiy o’rganishning ma’lumotlari turli davolash rejalari haqidagi mulohazalarni ehtimoliy bemorning oqibalaridan to’play oladilar.
There are numerous ways to create these machine-learning systems, and perhaps the most promising models are those that mimic the relationship between neurons in the brain. These artificial neural networks can use millions of connections to tackle difficult tasks like image recognition, speech recognition, and even language translation. However, the more self-directed these models become, the harder it is for computer scientists to determine how these self-taught algorithms arrive at their solution. Researchers are already looking at ways to make machine learning more transparent. But as AI becomes more involved in our everyday lives, these enigmatic decisions have increasingly large impacts on our work, health, and safety. So as machines continue learning to investigate, negotiate and communicate, we must also consider how to teach them to teach each other to operate ethically.
O’zi o’rganadigan mashinalar yaratishning bir qancha yo’llari bor, va ehtimol eng optimal model miyadagi neyronlar orasidagi bog’lanishni o’xshatishdir. Bu sun’iy neyron bog’lamalari millionlab bog’lanishlarni qiyin muammolarni yechishda ishlata oladilar: surat, ovoz aniqlash va hattoki til tarjima qilish. Biroq, qanchalik o’zia yo’nalgan model bo’lsa, dasturchilar uchun shunchalik bu o’zi o’rgatilgan algoritmlar ishlashini aniqlash qiyin bo’ladi. Tadqiqotchilar o’zi o’rganadigan mashina- lar yaratishni yo’llarini ko’rmoqdalar. Biroq SI ko’proq hayotimizga aralashar ekan, bunday o’ylantiradigan qarorlarning ko’proq ish, sog’liq va xavfsizligimizga ta’siri bor. Shunday qilib mashinalar qidirishni, kelishish va gaplashishni o’rganar ekan, biz ularning bir-biriga to’g’ri o’rgatishini ham hisobga olishimiz kerak.