Sequence Model
Course Link Lecture 5 in Deep Learning RNN there is one-to-many. So, this was a music generation or sequenced generation as example. And then, there’s many-to-one, that would be an example of sen
Tag: ML Analysis
ARIMA model
정상성(stationarity) 시계열은 시계열의 특징이 해당 시계열이 관측된 시간에 무관 추세나 계절성이 있는 시계열은 정상성을 나타내는 시계열이 아님 → 추세와 계절성은 서로 다른 시간에 시계열의 값에 영향을 줄 것이기 때문. 백색 잡음(white noise) 시계열: 정상성을 나타내는 시계열 → 언제 관찰하는지에 상관이 없고 시간에 따라 어떤 시점에서
Convolutional Neural Networks
Course Link Lecture 4 in Deep Learning CNN By convention, in machine learning, we usually do not bother with this flipping operation. Technically this operation is maybe better called cross-corre
Structuring Machine Learning Projects
Course Lecture 3 in Deep Learning Why ML Strategy F1 score Classifier A is 90% recall: That of all of the images in, say, your dev sets that really are cats, classifier A accurately pulled out 9
Imporoving Deep Neural Networks, Hyper parameter tuning, Regularization and Optimization
Course Lecture 2 in Deep Learning Regularization useful technique for reducing variance. There is a little bit of a bias variance tradeoff when you use regularization. It might increase the bias a li
Neural Networks and Deep Learning
Course Lecture 1 of Deep Learning Course Derivatives https://community.deeplearning.ai/t/derivation-of-dl-dz/165 vectorizing logistic regression Why we like to use that cost function for logistic re
Ecommerce Reorder Prediction
개요 유저들의 재주문 여부 예측하기 instacart kaggle: https://www.kaggle.com/competitions/instacart-market-basket-analysis/leaderboard 2위 한 모델 github: https://github.com/KazukiOnodera/Instacart 필요 메모리 약 300GB RAM이 필
Unsupervised Learning, Recommenders, Reinforcement Learning
Course Lecture 3 in Machine Learning course Unsupervised Learning1. clustering Usage: Grouping similar news, DNA analysis, Astronomical data analysis k-means algorithm local minimum Occurs when
Advanced Learning Algorithms
Course Lecture 2 in Machine Learning Course Neural Networks matrix multiplication: it is a binary operation that takes a pair of matrices and produces another matrix. It is defined as the product of
Supervised Machine Learning, Regression and Classification
Course Lecture 1 in Machine Learning Course Regression with multiple input variables1. vectorization Many CPUs have “vector” or “SIMD” instruction sets which apply the same operation simultaneously