-
Notifications
You must be signed in to change notification settings - Fork 58
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Muhyun Kim
authored and
Aston Zhang
committed
Aug 29, 2019
1 parent
41b649a
commit d4f3286
Showing
1 changed file
with
155 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,155 @@ | ||
| ## 영어-한국어 용어 비교표 | ||
|
|
||
| | 영어 | 한국어 | | ||
| | ------------------------------------------------ | ----------------------------- | | ||
| | access parameters | 액세스 파라미터 | | ||
| | accuracy | 정확도 | | ||
| | activation function | 활성화 함수 | | ||
| | attention model | 어텐션 모델 | | ||
| | average pooling layer | 평균 풀링 층 | | ||
| | backpropagation | 역전파 | | ||
| | baseline | 기준선 | | ||
| | batch | 배치 | | ||
| | bias | 편향 | | ||
| | bidirectional recurrent neural network | 양방향 리커런트 뉴럴 네트워크 | | ||
| | binary classification | 이진 분류 | | ||
| | block | 블록 | | ||
| | bucketing | | | ||
| | channel | 채널 | | ||
| | class | 클래스 | | ||
| | classification | 분류 | | ||
| | classifier | 분류기 | | ||
| | co-occurrence frequency | | | ||
| | collaborative filtering | | | ||
| | concatenate | 연결 | | ||
| | context | 컨텍스트 | | ||
| | context variable | | | ||
| | context vector | | | ||
| | context window | | | ||
| | context word | | | ||
| | continous bag-of-words (CBOW) model | | | ||
| | converge | | | ||
| | convex optimization | | | ||
| | convolutional | 컨볼루셔널 | | ||
| | convolutional layer | 컨볼루셔널 층 | | ||
| | convolutional neural network | | | ||
| | cost | | | ||
| | covariate shift | 공변량 변화 | | ||
| | cross-entropy | | | ||
| | cross-entropy loss | 크로스-엔트로피 손실 | | ||
| | data instance | | | ||
| | dataset | 데이터셋 | | ||
| | decision boundary | | | ||
| | decoder | | | ||
| | dense | | | ||
| | dimension | 차원 | | ||
| | diverge | | | ||
| | dropout | 드롭아웃 | | ||
| | eigenvalue | | | ||
| | empirical risk minimization | | | ||
| | encoder | | | ||
| | end-to-end | | | ||
| | epoch | 에포크 | | ||
| | error | 오류 | | ||
| | example | | | ||
| | exploding gradient | 그래디언트 폭발 | | ||
| | feature | 특성 | | ||
| | feature map | | | ||
| | filter | | | ||
| | forward propagation | 순전파 | | ||
| | fully connected layer | 완전 연결층 | | ||
| | Gaussian distribution | 가우시안 분포 | | ||
| | generalization | | | ||
| | generalization error | | | ||
| | gradient | 그래디언트 | | ||
| | gradient clipping | | | ||
| | gradient descent in one-dimensional space | | | ||
| | Gram matrix | | | ||
| | ground truth | | | ||
| | hidden layer | 은닉층 | | ||
| | hidden variable | | | ||
| | hyperparameter | 하이퍼파라미터 | | ||
| | hypothesis | | | ||
| | identity mapping | | | ||
| | image | | | ||
| | independent and identically distributed (i.i.d.) | | | ||
| | inference | 추론 | | ||
| | instance | | | ||
| | iterator | 이터레이터 | | ||
| | kernel | | | ||
| | label | 레이블 | | ||
| | layer | 층 | | ||
| | learning rate | 학습 속도 | | ||
| | linear model | | | ||
| | linear regression | | | ||
| | local minimum | | | ||
| | log likelihhod | 로그 가능도 | | ||
| | loss function | 손실 함수 | | ||
| | machine learning | 머신 러닝 | | ||
| | marginalization | 주변화 | | ||
| | mean | | | ||
| | mean squared error | | | ||
| | metric | | | ||
| | mini-batch | | | ||
| | mini-batch gradient | | | ||
| | model complexity | | | ||
| | model parameter | | | ||
| | momentum (method) | | | ||
| | multilayer perceptron | 다층 퍼셉트론 | | ||
| | negative sampling | | | ||
| | neural network | 뉴럴 네트워크 | | ||
| | non-convex optimization | | | ||
| | normalization | | | ||
| | numerical method | | | ||
| | object detection | | | ||
| | objective function | 목적 함수 | | ||
| | offset | | | ||
| | one hot encoding | 원-핫-인코딩 | | ||
| | operator | | | ||
| | optimization algorithm | 최적화 알고리즘 | | ||
| | optimizer | | | ||
| | outlier | 이상치 | | ||
| | overfitting | 오버피팅 | | ||
| | padding | | | ||
| | parameter | 파라미터 | | ||
| | partial derivative | | | ||
| | perplexity | | | ||
| | pipeline | | | ||
| | pooling layer | | | ||
| | property | | | ||
| | pseudo | 의사 | | ||
| | random variable | 확률 변수 | | ||
| | receptive field | | | ||
| | recurrent neural network | | | ||
| | regression | 회귀 | | ||
| | saddle point | | | ||
| | scalar | 스칼라 | | ||
| | sentiment analysis | | | ||
| | shape | 모양 | | ||
| | skip-gram model | | | ||
| | softmax regression | | | ||
| | softmax，hierarchical softmax | | | ||
| | stochastic gradient descent | 확률적 경사 하강법 | | ||
| | stride | | | ||
| | subsample | | | ||
| | support vector machine | | | ||
| | test dataset | 테스트 데이터셋 | | ||
| | tokenizer/tokenization | | | ||
| | training dataset | 학습 데이터셋 | | ||
| | training error | | | ||
| | transform | | | ||
| | tune hyper-parameter | | | ||
| | unbiased estimate | | | ||
| | underfitting | 언더피팅 | | ||
| | uniform sampling | | | ||
| | unknown token | | | ||
| | update model parameter(s) | | | ||
| | upsample | | | ||
| | validation dataset | 검증 데이터셋 | | ||
| | vanishing gradient | 그래디언트 소실 | | ||
| | variance | | | ||
| | vector | 벡터 | | ||
| | weight | | | ||
| | word embedding | | | ||
| | word vector | | | ||
| | zero tensor | | |