Différences

Ci-dessous, les différences entre deux révisions de la page.

Lien vers cette vue comparative

Les deux révisions précédentesRévision précédente
Prochaine révision
Révision précédente
documentation:algorithms:pattern-recognition-algorithms [2023/01/19 10:31] – supprimée - modification externe (Unknown date) 127.0.0.1documentation:algorithms:pattern-recognition-algorithms [2023/01/19 12:07] (Version actuelle) baudryj
Ligne 1: Ligne 1:
 +====== Pattern recognition algorithms used in data science ======
  
 +  * K-Nearest Neighbors (KNN)
 +  * Linear Discriminant Analysis (LDA)
 +  * Quadratic Discriminant Analysis (QDA)
 +  * Decision Trees
 +  * Random Forest
 +  * Naive Bayes
 +  * Support Vector Machines (SVMs)
 +  * Neural Networks (including Deep Learning)
 +  * k-means
 +  * Hierarchical clustering
 +  * DBSCAN
 +  * Principal Component Analysis (PCA)
 +  * Independent Component Analysis (ICA)
 +  * Non-Negative Matrix Factorization (NMF)
 +  * Singular Value Decomposition (SVD)
 +
 +===== With time series data, some common pattern recognition algorithms include =====
 +
 +  * Time Series Decomposition: decomposing a time series into its components such as trend, seasonality and noise
 +  * Exponential smoothing: used for forecasting and estimating the trend in time series data
 +  * ARIMA: a class of statistical models for analyzing and forecasting time series data
 +  * Seasonal decomposition of time series by Loess (STL): decompose time series into seasonal, trend, and residual components
 +  * Dynamic Time Warping (DTW): a technique for measuring similarity between two temporal sequences, often used in time series classification
 +  * Hidden Markov Models (HMM): used for modeling sequential data, such as stock prices or speech signals.
 +  * Additionally, Recurrent Neural Networks (RNN) and its variants such as LSTM and GRU are also very effective in time series analysis and prediction tasks.
 +
 +<html>
 +<iframe style="border:none" width="100%" height="450" src="https://whimsical.com/embed/LHSHLepbY3RjYoLjFefJLE"></iframe>
 +</html>
Haut de page