Orange: Manifold Learning

Sumber: https://docs.biolab.si//3/visual-programming/widgets/unsupervised/manifoldlearning.html

Nonlinear dimensionality reduction.

Input

Data: input dataset

Output

Transformed Data: dataset with reduced coordinates

Manifold Learning is a technique which finds a non-linear manifold within the higher-dimensional space. The widget then outputs new coordinates which correspond to a two-dimensional space. Such data can be later visualized with Scatter Plot or other visualization widgets.

• Method for manifold learning:
  • t-SNE
  • MDS, see also MDS widget
  • Isomap
  • Locally Linear Embedding
  • Spectral Embedding
• Set parameters for the method:
  • t-SNE (distance measures):
    • Euclidean distance
    • Manhattan
    • Chebyshev
    • Jaccard
    • Mahalanobis
    • Cosine
  • MDS (iterations and initialization):
    • max iterations: maximum number of optimization interactions
    • initialization: method for initialization of the algorithm (PCA or random)
  • Isomap:
    • number of neighbors
  • Locally Linear Embedding:
    • method:
      • standard
      • modified
      • hessian eigenmap
      • local
    • number of neighbors
    • max iterations
  • Spectral Embedding:
    • affinity:
      • nearest neighbors
      • RFB kernel
• Output: the number of reduced features (components).
• If Apply automatically is ticked, changes will be propagated automatically. Alternatively, click Apply.
• Produce a report.

Manifold Learning widget produces different embeddings for high-dimensional data.

From left to right, top to bottom: t-SNE, MDS, Isomap, Locally Linear Embedding and Spectral Embedding.

Contoh

Manifold Learning widget transforms high-dimensional data into a lower dimensional approximation. This makes it great for visualizing datasets with many features. We used voting.tab to map 16-dimensional data onto a 2D graph. Then we used Scatter Plot to plot the embeddings.

Referensi

• https://docs.biolab.si//3/visual-programming/widgets/unsupervised/manifoldlearning.html

Pranala Menarik

• Orange