본문 바로가기

분류 전체보기

 (79)
[Deep Learning Architecture] CNN, RNN, Attention-based CNN Model CNN이란? 이미지 처리에서 많이 사용되며 cnvolution과 pooling을 반복적으로 진행하는 구조 Time series data의 CNN 적용 Dilated Convolutions 기존의 convolution의 계산을 줄여주기 위해 도입 이미지 처리에서의 dilated convolution은 filter matrix 사이에 0을 삽입하여, Receptive field 의 크기는 늘리고, 계산량은 감소 1차원 convolution 필터를 활용해 입력되는 sequence 무시가 데이터 간의 가중합 (Weighted sum)을 구하여 예측 대상인 미래 값을 산출 할 수 있다. 하나 cnn구조는 과거와 미래 데이터간에 시간적인 의존성에 대해서는 고려하지 않는다. RNN Model 자연어..
[논문리뷰]Time Series Forecasting With Deep Learning A Survey Time Series Forecasting With Deep Learning A Survey https://arxiv.org/pdf/2004.13408.pdf Numerous deep learning architectures have been developed to accommodate the diversity of time series datasets across different domains. In this article, we survey common encoder and decoder designs used in both one-step-ahead and multi-horizon time series forecasting – describing how temporal information is ..
데이터처리 파이프라인 프레임워크 https://haje01.github.io/2020/04/21/snakemake-tutorial.html 스네이크메이크 (Snakemake) 튜토리얼 haje01의 노트 haje01.github.io 깃헙보면서 정리 예정
[Machine Learning]Linear regression with one variable - cost function intuition1 Coursera lecture summary Cost function intuition 1 When \theta_1 = 1θ1 = 1θ1​=1, we get a slope of 1 which goes through every single data point in our model. Conversely, when \theta_1 = 0.5θ1​=0.5, we see the vertical distance from our fit to the data points increase.
Linear regression with one variable - Cost function Coursera lecture summary Cost function We can measure the accuracy of our hypothesis fufnction by using a cost functon. This takes an acerage difference (actually a fancier version of an average) of all the results of the hypothesis with inputs from x's and the actual output y's To break it apart, it is 1/2x where x is the mean of the squares of h@(Xi)-yi, or the difference between the predicted..
Linear regression with one variable - Model Representation Coursera lecture summary Model Representation To estabkusg itauib for future use, we 'll use x(i) to denote the "input" baribles(livibg area in the example), also called input features, and y(i) ti denote the "output" or target variable that we are trying to predict(price). A pair(x(i), y(i)) is called a training example, and the datset that we'll ve using th learn-a list of m training examples ..
Supervised Learning & Unsupervised Learning Coursera lecture summary Supervised Learning & Unsupervised Learning Supervised Learning In supervised learning, we are given a data set and already know what our correct output should look like, having the idea that there is a reltionship betwwen the input and the output. Supervised learning problems ar categorized into "regression" and "Classification" problems. In a regression problem, we are..
Supervised Learning & Unsupervised Learning Coursera lecture summary Supervised Learning & Unsupervised Learning Supervised Learning In supervised learning, we are given a data set and already know what our correct output should look like, having the idea that there is a reltionship betwwen the input and the output. Supervised learning problems ar categorized into "regression" and "Classification" problems. In a regression problem, we are..

티스토리툴바