hõlmab tehnoloogiaid, kus masin õpib andmete põhjal iseseisvalt ülesandeid täitma – näiteks pilte analüüsima, kõnet ära tundma, andmete põhjal otsuseid langetama või prognoose tegema
application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed
the process by which a [software entity or a hardware entity equipped with software components] improves its performance by acquiring new knowledge or skills, or by reorganizing [its] existing knowledge or skills
Hea teada
Masinõpe sai alguse 1950. aastatel, kui Arthur Samuel valmistas kabet mängiva programmi.
Hea teada
Machine learning is often used for natural language processing and computer vision, and to establish diagnoses and forecasts.
Unsupervised learning, also known as unsupervised machine learning, uses machine learning algorithms to analyze and cluster unlabeled datasets. These algorithms discover hidden patterns or data groupings without the need for human intervention.—IBM Supervised machine learning requires labeled data to adjust the parameters of the model during training. … But without quality training data, supervised learning models will end up making poor inferences.—Ben Dickson Reinforcement machine learning trains machines through trial and error to take the best action by establishing a reward system. Reinforcement learning can train models to play games or train autonomous vehicles to drive by telling the machine when it made the right decisions, which helps it learn over time what actions it should take.—Sara Brown
Kuigi masinõpe on oluline tehisintellekti haru, ei piirdu TI ainult sellega. Masinõpe keskendub süsteemide võimele ise õppida ja kohaneda, samas kui TI võib hõlmata ka reeglipõhiseid süsteeme. Masinõpe on eriti kasulik masintõlkesüsteemide loomisel, sest ülesanne nõuab võimet õppida keerulisi grammatilisi struktuure ja sõnavara suurtest tekstikogudest.
