Giter Site home page Giter Site logo

1교시 about cup_deeplearning_seminar HOT 10 OPEN

diginori avatar diginori commented on June 13, 2024
1교시

from cup_deeplearning_seminar.

Comments (10)

diginori avatar diginori commented on June 13, 2024

코드랩에 github 링크를 올려서 편집 및 실행
https://colab.research.google.com/github/diginori/cup_deeplearning_seminar/blob/master/%EA%B5%90%EC%9C%A1%EC%9E%90%EB%A3%8C/deep_learning/keras_and_dnn.ipynb

from cup_deeplearning_seminar.

diginori avatar diginori commented on June 13, 2024

데이터셋

tran - 학습
valid - 학습 검증
test - 학습 잘되엇나 확인

from cup_deeplearning_seminar.

diginori avatar diginori commented on June 13, 2024

AI 연구원, 머신러닝이 연금술에 불과하다고 역설

https://github.com/jehyunlee/texts/blob/master/AI_researchers_allege_that_machine_learning_is_alchemy/text.md

from cup_deeplearning_seminar.

diginori avatar diginori commented on June 13, 2024

verbose=1 하면 진행 상태가 보인다.

image

from cup_deeplearning_seminar.

diginori avatar diginori commented on June 13, 2024

딥러닝

  • 데이터가 어떤 데이터인가요?
  • 전처리
  • 노말라이션은요?
  • 셔플은요? ( 모델 만들때 트레이닝 테스트 할때 )

-> 위의 것이 잘못되면 학습이 안되는 결과다.

from cup_deeplearning_seminar.

diginori avatar diginori commented on June 13, 2024

Normalization/Standardization
입력이 여러 차원일 때 각 차원의 입력을 동일한 스케일로 맞추어주면, 학습이 빠르게 진행된다고 한다.

Normalization : 전체 데이터를 0~1로 변환해준다. 키를 ... (꼭 해준다)
Standardization : 평균을 0, 표준편차를 1이되도록 변환해 준다. (꼭은 아니다)

from cup_deeplearning_seminar.

diginori avatar diginori commented on June 13, 2024

http://taewan.kim/post/norm/ 에서 Regularization 설명 할 때

from cup_deeplearning_seminar.

diginori avatar diginori commented on June 13, 2024

Epoch이란?
전체 sample 데이터를 이용하여 한 바퀴 돌며 학습하는 것을 1회 epoch이라 부른다.
따라서 2 epochs은 전체 sample을 이용하여 두 바퀴를 돌며 학습한 것이다.

Step이란?

Weight와 Bias를 1회 업데이트하는 것을 1 Step이라 부른다.

Batch Size란?

1회 Step에서 사용한 데이터의 수이다.

따라서 Batch Size가 100이라고 가정하고 Step이 5이면 약 500개의 데이터를 이용한 것이다.

아래와 같은 관계가 성립한다.

s = (n * e) / b

https://m.blog.naver.com/PostView.nhn?blogId=wideeyed&logNo=221333529176&proxyReferer=https%3A%2F%2Fwww.google.com%2F

from cup_deeplearning_seminar.

diginori avatar diginori commented on June 13, 2024

Keras Sequential 모델로 시작하기
https://www.codeonweb.com/entry/fe7882d2-e42a-4ef3-bbc2-e616d366e013

from cup_deeplearning_seminar.

diginori avatar diginori commented on June 13, 2024

종료 - https://colab.research.google.com/drive/1_5SImHxKgw3eGCynRNzFM6tj4fAbO2t1

from cup_deeplearning_seminar.

Related Issues (9)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.