deep learning
süvaõpe
olemus
(1) inimkontekstis:
põhjalik, erinevalt pealiskaudsemast
= an approach and an attitude to learning, where the learner uses higher-order cognitive skills such as the ability to analyse, synthesize, solve problems, and thinks meta-cognitively in order to construct long-term understanding
http://www.julianhermida.com/algoma/law1scotldeeplearning.htm
(2) masinõppe haru:
põhineb mitmekihilise abstraheerimisega mittelineaarmudelitel
= a subset of machine learning, which is essentially a neural network with three or more layers
https://www.youtube.com/watch?v=He4t7Zekob0
ISO/IEC 22989:
(intellektitehnikas) meetod sisukate hierarhiliste esituste loomiseks paljude varjatud kihtidega neurovõrkude treenimise teel; süvaõpe on masinõppe alaliik
= (artificial intelligence) approach to creating rich hierarchical representations through the training of neural networks with many hidden layers
Note. Deep learning is a subset of ML
https://en.wikipedia.org/wiki/Deep_learning
https://www.cs.tau.ac.il/~dcor/Graphics/pdf.slides/YY-Deep%20Learning.pdf
http://www.scholarpedia.org/article/Deep_Learning
https://d2l.ai/d2l-en.pdf
https://www.hindawi.com/journals/misy/2020/6535834/
https://www.mdpi.com/2078-2489/10/4/122/pdf
vt ka
- neurovõrk
- tehisintellekt