심층 학습, 딥 러닝, deep learning
기계학습,machine_learning의 구현 기법(technique) 중 하나로, 신경망,neural_network ( 심층신경망,deep_neural_network,DNN - 페이지를 여기와 따로 만들지 말지 tbd. { DNN, Deep Nets http://sanghyukchun.github.io/54/ 계층이 두터운 신경망,neural_network은, 가중값,weight들이 랜덤 보다는 정교하게 초기화,initialization되면 매우 잘 훈련될 수 있다는 것이 발견됨 (2006-2007년, Hinton and Bengio의 breakthrough.[1]) } ) 를 사용. thanks to Hinton's DBN = deep_belief_network in 2006.
보통 massive data가 필요?
보통 massive data가 필요?
장점
- requires little or no handcrafted feature extraction
신경세포(뉴런,neuron)를 mimic함.
forward propagation
input layer - hidden layer - output layer
경사 강하 gradient descent
lectures ¶
Andrew Ng 코세라 강의:
Neural Networks and Deep Learning | Coursera
https://www.coursera.org/learn/neural-networks-deep-learning
Neural Networks and Deep Learning | Coursera
https://www.coursera.org/learn/neural-networks-deep-learning
topix (tmp, via wpko) ¶
DNN deep_neural_network
CNN convolutional_neural_network
RNN recurrent_neural_network
RBM restricted_Boltzmann_machine
DBN deep_belief_network
심층 Q-네트워크(Deep Q-Networks) pagename?
...대부분 신경망,neural_network
CNN convolutional_neural_network
RNN recurrent_neural_network
RBM restricted_Boltzmann_machine
DBN deep_belief_network
심층 Q-네트워크(Deep Q-Networks) pagename?
...대부분 신경망,neural_network
tmp links ko ¶
딥러닝
DS-GA 1008 · 2020 봄 · NYU CENTER FOR DATA SCIENCE
강사 - 얀 르쿤 & 알프래도 캔지아니
https://atcold.github.io/pytorch-Deep-Learning/ko/
DS-GA 1008 · 2020 봄 · NYU CENTER FOR DATA SCIENCE
강사 - 얀 르쿤 & 알프래도 캔지아니
https://atcold.github.io/pytorch-Deep-Learning/ko/
Kaggle 사이트의 intro
https://www.kaggle.com/learn/intro-to-deep-learning
그걸 바탕으로 정리한 ko 글
https://webnautes.tistory.com/1646
https://www.kaggle.com/learn/intro-to-deep-learning
그걸 바탕으로 정리한 ko 글
https://webnautes.tistory.com/1646
UNIGE 14x050 – Deep Learning
https://fleuret.org/dlc/
François Fleuret's deep-learning courses 14x050 of the University of Geneva, Switzerland
https://fleuret.org/dlc/
François Fleuret's deep-learning courses 14x050 of the University of Geneva, Switzerland