Learning to Learn

Hold-out vs. Cross-validation in Machine Learning

I recently wrote about holdout and cross-validation in my post about building a k-Nearest Neighbors (k-NN) model to predict diabetes. Last…

medium.com

Tensor / 텐서

Find the rhythm in the mathematics and you will fare pretty well!​대학 과정에서 tensor를 처음 접하...

blog.naver.com

What is Inductive Bias? | Inductive Bias

Inductive bias is the set of assumptions a learner uses to predict results given inputs it has not yet encountered. It’s also the name of this blog. Let’s talk about swans. Let’s suppose you don’t know anything about swans. You decide to visit Swan River i

inductivebias.com

Norm의 종류( 마할라노비스(Mahalanobis Distance), 유클리디언(Euclidean Distance) )

Norm이란선형대수학에서 벡터공간의 원소들에 일종의 '길이'를 부여하는 함수이다 ---위키백과즉, '길이'...

blog.naver.com

컴공생의 AI 스쿨 필기 노트 ④ 교차 검증과 정규화

Cross Validation & Regularization | 지금까지 Linear Regression, Logistic Regression 모델을 만들어보았는데요. 우리가 만든 모델이 과연 잘 만들어진 모델이라고 볼 수 있을까요? 이를 알기 위해서 이번 4주차 수업에서는 우리가 만든 모델의 적합성을 보다 객관적으로 평가하기 위한 방법으로 교차 검증(Cross Validation)과 정규화(Regularization)

brunch.co.kr

Understanding Categorical Cross-Entropy Loss, Binary Cross-Entropy Loss, Softmax Loss, Logistic Loss, Focal Loss and all those c

People like to use cool names which are often confusing. When I started playing with CNN beyond single label classification, I got confused with the different names and formulations people write in their papers, and even with the loss layer names of the de

gombru.github.io

Understanding Ranking Loss, Contrastive Loss, Margin Loss, Triplet Loss, Hinge Loss and all those confusing names

After the success of my post Understanding Categorical Cross-Entropy Loss, Binary Cross-Entropy Loss, Softmax Loss, Logistic Loss, Focal Loss and all those confusing names, and after checking that Triplet Loss outperforms Cross-Entropy Loss in my main rese

gombru.github.io