Unexplainable Explanations: Towards Interpreting tSNE and UMAP Embeddings.
Andrew DraganovSimon DohnPublished in: CoRR (2023)
Keyphrases
- generating explanations
- vector space
- low dimensional
- three dimensional
- manifold learning
- domain theory
- distance measure
- hilbert space
- euclidean space
- neural network
- dimensionality reduction
- artificial neural networks
- data structure
- multi agent
- causal models
- multiscale
- binary codes
- artificial intelligence
- information retrieval