Evaluating MASHAP as a faster alternative to LIME for model-agnostic machine learning interpretability.
Andreas MessalasChristos AridasYiannis KanellopoulosPublished in: IEEE BigData (2020)
Keyphrases
- machine learning
- probabilistic model
- high level
- mathematical model
- prior knowledge
- probability distribution
- statistical model
- learning models
- genetic algorithm
- formal model
- experimental data
- process model
- computational model
- text classification
- input data
- natural language processing
- database
- cost function
- artificial neural networks
- data analysis
- multiscale
- similarity measure
- case study