Low Rank Approximation (LRA) Methods - (SVD, PCA, t-SNE ...)

< 목차 >

• Why and What is Dimension Reduction ?
• Singular Vector Decomposition (SVD)
• Pricipal Component Analysis (PCA)
  • AutoEncoder (with 2 hidden dim) vs PCA
• Latent Dirichlet Allocation (LDA)
• t-distributed Stochastic Neighbor Embedding (t-SNE)
• Fisher's linear discriminant
• References

Why and What is Dimension Reduction ?

Singular Vector Decomposition (SVD)

Pricipal Component Analysis (PCA)

AutoEncoder (with 2 hidden dim) vs PCA

Latent Dirichlet Allocation (LDA)

t-distributed Stochastic Neighbor Embedding (t-SNE)

Fisher's linear discriminant

References

• Introduction to Low Rank Approximation, Dimension Reduction, and Clustering from Haesun Park
• Bishop, Christopher M. Pattern recognition and machine learning. springer, 2006.
• PCA - Principal Component Analysis