Overfitting
- If the neral network is large and deep enough, the neral network can achieve zero loss for the training dataset.
- It can memorize the answer to every problem in the dataset.
- Without a proper understanding of the problem
- We call it Overfitting
- It can even memorize random trash dataset.
- A neural network can reduce the training loss that has no pattern at all.
https://developers.google.com/machine-learning/crash-course/generalization/peril-of-overfitting
Generalization: Peril of Overfitting | Machine Learning | Google Developers
Send feedback Generalization: Peril of Overfitting Stay organized with collections Save and categorize content based on your preferences. Estimated Time: 10 minutes This module focuses on generalization. In order to develop some intuition about this concep
developers.google.com
Hyperprameters
- Hyperparameters are settings that can affect the training of parameters.
- Some examples:
Number of layers, Size of each layer, Structure of neural network, Learing rate, Number of training iteration, Loss function
Hyperparameter Overfitting
- The specific hyperparameters that we have used was tested only with a specific test set.
- We cannot assure that the same setting works well with anoter unseen dataset.
- Therefore, we use another dataset called the validation set.
- So dataset is split into train / valid / test
- Instead of checking the accuracy on the test set, we use the validation set.
- We must not checking the accuracy until the very last stage.
- Parameters are trained with the Training set, and Hyperparameters are selected with the validation set.
번외)
머신 러닝에 관한 좋은 레퍼런스 링크
https://developers.google.com/machine-learning/crash-course/ml-intro
머신러닝 소개 | Machine Learning | Google Developers
이 페이지는 Cloud Translation API를 통해 번역되었습니다. Switch to English 의견 보내기 머신러닝 소개 컬렉션을 사용해 정리하기 내 환경설정을 기준으로 콘텐츠를 저장하고 분류하세요. 이 모듈에서
developers.google.com
Accuracy in Machine Learning
https://developers.google.com/machine-learning/crash-course/classification/accuracy
분류: 정확성 | Machine Learning | Google Developers
이 페이지는 Cloud Translation API를 통해 번역되었습니다. Switch to English 의견 보내기 분류: 정확성 컬렉션을 사용해 정리하기 내 환경설정을 기준으로 콘텐츠를 저장하고 분류하세요. 예상 시간: 6분
developers.google.com
'정리 > Data&AI' 카테고리의 다른 글
활성화 함수와 손실 함수 (0) | 2022.10.20 |
---|---|
Batch와 Epoch (0) | 2022.10.13 |
손실 함수, 경사 하강법, 역전파 (0) | 2022.09.22 |
Python에서 OOP하기 (0) | 2022.09.14 |
Jupyter Notebook관련 이것 저것 (0) | 2022.09.14 |