Difference between revisions of "Dimensional Reduction"
| Line 14: | Line 14: | ||
* [[t-Distributed Stochastic Neighbor Embedding (t-SNE)]] | * [[t-Distributed Stochastic Neighbor Embedding (t-SNE)]] | ||
* [[Softmax]] | * [[Softmax]] | ||
| + | * [http://github.com/JonTupitza/Data-Science-Process/blob/master/06-Dimensionality-Reduction.ipynb Dimensionality Reduction Techniques Jupyter Notebook] | [http://github.com/jontupitza Jon Tupitza] | ||
* [[Local Linear Embedding (LLE) | Embedding functions]] | * [[Local Linear Embedding (LLE) | Embedding functions]] | ||
| − | |||
| − | |||
To identify the most important [[Feature Exploration/Learning | Features]] to address: | To identify the most important [[Feature Exploration/Learning | Features]] to address: | ||
| Line 23: | Line 22: | ||
* 2D & 3D intuition often fails in higher dimensions | * 2D & 3D intuition often fails in higher dimensions | ||
* distances tend to become relatively the 'same' as the number of dimensions increases | * distances tend to become relatively the 'same' as the number of dimensions increases | ||
| − | |||
* Algorithms: | * Algorithms: | ||
Revision as of 07:35, 5 April 2020
Youtube search... ...Google search
- Pooling / Sub-sampling: Max, Mean
- Kernel Trick
- Isomap
- Local Linear Embedding (LLE)
- t-Distributed Stochastic Neighbor Embedding (t-SNE)
- Softmax
- Dimensionality Reduction Techniques Jupyter Notebook | Jon Tupitza
- Embedding functions
To identify the most important Features to address:
- reduce the amount of computing resources required
- 2D & 3D intuition often fails in higher dimensions
- distances tend to become relatively the 'same' as the number of dimensions increases
- Algorithms:
- Principal Component Analysis (PCA)
- Independent Component Analysis (ICA)
- Canonical Correlation Analysis (CCA)
- Linear Discriminant Analysis (LDA)
- Multidimensional Scaling (MDS)
- Non-Negative Matrix Factorization (NMF)
- Partial Least Squares Regression (PLSR)
- Principal Component Regression (PCR)
- Projection Pursuit
- Sammon Mapping/Projection
Related:
- (Deep) Convolutional Neural Network (DCNN/CNN)
- Factor analysis
- Feature extraction
- Feature selection
- Seven Techniques for Dimensionality Reduction | KNIME
- Nonlinear dimensionality reduction | Wikipedia
Some datasets may contain many variables that may cause very hard to handle. Especially nowadays data collecting in systems occur at very detailed level due to the existence of more than enough resources. In such cases, the data sets may contain thousands of variables and most of them can be unnecessary as well. In this case, it is almost impossible to identify the variables which have the most impact on our prediction. Dimensional Reduction Algorithms are used in this kind of situations. It utilizes other algorithms like Random Forest, Decision Tree to identify the most important variables. 10 Machine Learning Algorithms You need to Know | Sidath Asir @ Medium
