Difference between revisions of "Principal Component Analysis (PCA)"
Line 15: | Line 15: | ||
* [[T-Distributed Stochastic Neighbor Embedding (t-SNE)]] | * [[T-Distributed Stochastic Neighbor Embedding (t-SNE)]] | ||
* [http://www.cs.helsinki.fi/u/ahyvarin/whatisica.shtml Independent Component Analysis (ICA) | University of Helsinki] | * [http://www.cs.helsinki.fi/u/ahyvarin/whatisica.shtml Independent Component Analysis (ICA) | University of Helsinki] | ||
+ | ** [http://www.cs.helsinki.fi/u/ahyvarin/papers/JMLR06.pdf Linear Non-Gaussian Acyclic Model (ICA-LiNGAM)] | S. Shimizu, P. Hoyer, A. Hyvarinen, and A. Kerminen - University of Helsinki] | ||
a data reduction technique that allows to simplify multidimensional data sets to 2 or 3 dimensions for plotting purposes and visual variance analysis. | a data reduction technique that allows to simplify multidimensional data sets to 2 or 3 dimensions for plotting purposes and visual variance analysis. |
Revision as of 10:41, 22 June 2019
YouTube search... ...Google search
- AI Solver
- ...find outliers
- Clustering
- Anomaly Detection
- Dimensional Reduction Algorithms
- T-Distributed Stochastic Neighbor Embedding (t-SNE)
- Independent Component Analysis (ICA) | University of Helsinki
- Linear Non-Gaussian Acyclic Model (ICA-LiNGAM) | S. Shimizu, P. Hoyer, A. Hyvarinen, and A. Kerminen - University of Helsinki]
a data reduction technique that allows to simplify multidimensional data sets to 2 or 3 dimensions for plotting purposes and visual variance analysis.
- Center (and standardize) data
- First principal component axis
- Across centroid of data cloud
- Distance of each point to that line is minimized, so that it crosses the maximum variation of the data cloud
- Second principal component axis
- Orthogonal to first principal component
- Along maximum variation in the data
- First PCA axis becomes x-axis and second PCA axis y-axis
- Continue process until the necessary number of principal components is obtained
NumXL