Localization, Detection and Segmentation
2018-11-14
Image Classification이 아닌 다양한 Computer Vision Task 소개와 CNN Approach관점의 알고리즘 알아보겠습니다.
확률이론-전통적인 확률 모델(Probability Model)
2018-11-13
- 정리
- Introduction a Generative Model(생성모델)
- 이항분포(Binomial Distribution)
- 베르누이분포
- 정규분포(Normal Distribution)
- 가우시안분포
- 다항분포(Multinomial Distribution)
- 베르누이시행/베르누이독립시행
- Likelihood와 Probability의 차이
- Likelihood(가능도)
- Log-likelihood
- Estimator 종류
- XX-Likelihood Estimation(가능도 추정량)
- MLE(Maximum Likelihood Estimation)
- Discriminative Approach & Generative Approach
- GDA(Gaussian Discriminant Analysis)
- GMM(Gaussian Mixture Model) = MoG(Mixture of Gaussian)
- EM(Expectation Maximization)
- Residual
- Cost=Error=오차=손실=비용
- Cross entropy error, CEE (교차 엔트로피 오차)
- Linear Regression
- Logistic Regression(Binary Classification) vs Multinomial Logistic Regression = Softmax(Multinomial Classification)
- Naïve Bayes
- Gaussian Discriminant Analysis
- Joint Likelihood
- Joint Probability
- Analytic solution
- 모수(Parameters)
- Bayes’ Rule
- Expectation
- Lower Bound of Log-likelihood
- Lower Bound of Log-likelihood = Log-likelihood 함수의 평균(기대값)을 의미?
- Jensen’s Inequality
- Posterior Probability(사후확률) / Prior Probability(사전확률)
Demo post displaying the various ways of highlighting code in Markdown.
Hello gitpage post with markdown
2018-11-04
- markdown file
- test
- 샘플
- 블로그 포스트
- cheat sheet
- GAN
- CNN
- Reinforcement Learning
- Finance
- Entertainment
- Meta Learning
- cs231n
- One-Shot Learning
- Code
- Project
- Java
- MSA
- mysql
- Python
- Docker
- RNN
- LSTM
- 논문리뷰
- 논문구현
- Paper Review
- Paper Implement
- Kears
- Pytorch
- Tensorflow
- Fine Tuning
- Bayesian Statistic / Bayes’ Theorem / (> Bayes’ Rule)
- Attention(in RNN)
- Pr12
- Transfer Learning
- Hierarchical RL
- Dynamic Programming
- 계층형강화학습
- 역강화학습
- CUDA
- R2D2
- Likelihood
- Log-likelihood
- Likelihood Estimation
- MLE(Maximum Likelihood Estimation)
- MAP(Maximum a Posteriori Estimation)
- PDF(Probability Density Function)
- PMF(Probability Mass Function)
- GMM(Gaussian Mixture Model)
- EM(Expectation Maximization)
- ML(Probabilistic Perspective)
- 고전-통계학 vs 해석적?통계(베이지안)
- 독립(Independence)
- 결합확률(Joint Probability)
- 주변확률분포(Marginal Probability Distribution)
- 조건부확률(Conditional Probability)
- 전통적-Generative Model vs 딥-Generative Model
- independent and identical distributed(i.i.d.)
- Conjugate Prior
- 우도(Likelihood Probability)
- 사전확률(Prior Probability)
- 사후확률(Posterior Probability)
- 전확률 공식(Law of Total Probability) 또는 베이즈 법칙(Bayes’ Rule)
- 확률 이론
- 정보 이론
- Entropy
- KL-Divergence
- VAE(Variational Autoencoder)
- 정보엔트로피(Information Entropy)
- 분포(Distribution)
- 확률분포(Probability Distribution)
- 최소자승법(Linear Square)
- 최소평균제곱법(Linear Mean Square)
- Residual
- Cost=Error=오차=손실=비용
- Cross entropy error, CEE (교차 엔트로피 오차)
- Logistic Regression(Binary Classification) vs Multinomial Logistic Regression = Softmax(Multinomial Classification)
- Convex하다 Convex Function(볼록함수)
- Bernoulli Distribution / Gaussian Distribution
- Defining a Probability Distribution - Discrete Distribution(PMF) / Continuous Distribution(PDF)
- Conditional Distribution
- Expectations and Variance
- Some Important Distributions(Bernoulli/Poisson/Gaussian)
- Working with Probabilities(The log trick/Delayed Normalization/Jenson’s Inequality)
- 매니폴드러닝(Manifold Learning)
- 메타러닝(Meta Learning)
- 원샷러닝(One-shot Learning)
- 트랜스퍼러닝(Transfer Learning)
- 이미테이션러닝(Imitation Learning)
- 계층형강화학습(Hierarchical RL)
- 역강화학습(Inverse RL, IRL)
- 분산 강화학습(Distributed Prioritized Experience Replay RL)
- 능동학습(Active Learning)
This is just a sample. You can play around with your own text right here.
You're up and running!
Next you can update your site name, avatar and other options using the _config.yml file in the root of your repository (shown below).
A Full and Comprehensive Style Test
Below is just about everything you’ll need to style in the theme. Check the source code to see the many embedded elements within paragraphs.