Recurrent Neural Networks(RNN) 순환 신경망
2022. 9. 7. 11:37ㆍAI/인공지능 공부
반응형
RNN
Learn how recurrent neural networks use sequential data to solve common temporal problems seen in language translation and speech recognition.
1. RNN이란?
- a type of artificial neural network which uses sequential data or time series data.
- commonly used for ordinal or temporal problems
- language translation
- natural language processing (nlp)
- speech recognition
- image captioning
- commonly used for ordinal or temporal problems
- distinguished by their “memory” as they take information from prior inputs to influence the current input and output.
- traditional deep neural networks: inputs and outputs are independent of each other
- recurrent neural networks: outputs depend on the prior elements within the sequence
- While future events would also be helpful in determining the output of a given sequence, unidirectional recurrent neural networks cannot account for these events in their predictions.
각 요소를 판단할 때 이전 요소에 대한 정보가 들어와서 판단하는 데 영향을 주는 것이다.
아래는 RNN의 개념을 이해하는 데 도움이 된 영상 링크이다.
https://www.youtube.com/watch?v=oORGMrhsx0o
https://www.youtube.com/watch?v=PahF2hZM6cs
반응형
'AI > 인공지능 공부' 카테고리의 다른 글
Neural Network 신경망 (0) | 2022.09.06 |
---|