1. 딥러닝의 시작 뉴욕타임즈
False Promises “The Navy revealed the embryo of an electronic computer today that it expects will be able to walk, talk, see, write, reproduce itself an be conscious of its existence … Dr. Frank Rosenblatt, a research psychologist at the Cornell Aeronautical Laboratory, Buffalo, said Perceptrons might be fired to the planets as mechanical space explorers” July 08, 1958
2. 문제 봉착.. 해결 못함.
XOR problem: linearly separable?
3.Perceptrons
4.No one on earth had found a viable way to train
5. 해결
2. 또다시 문제가발생
10여개 이상의 이상의 학습은 문제가 되었다.
출처: 모두를 위한 딥러닝
'4Z1 - Artificial Intelligence > 인공지능 개론' 카테고리의 다른 글
Backpropagation -XOR (0) | 2020.08.27 |
---|---|
XOR 문제 딥러닝으로 풀기 (0) | 2020.08.27 |
Application & Tips:Learning rate, data preprocessing, overfitting (0) | 2020.08.27 |
딥러닝의 기본 학습 - Logistic (Regression) Classification -5 (0) | 2020.08.27 |
딥러닝의 기본 학습 - Logistic (Regression) Classification -이론,실습-4 (0) | 2020.08.27 |