What Makes a Good Diagnosis: An Algorithm to Detect Biased Training Data.
Madeleine SchneiderRobert ThomsonsPublished in: AAAI Spring Symposium: Interpretable AI for Well-being (2019)
Keyphrases
- learning algorithm
- detection algorithm
- training data
- matching algorithm
- high accuracy
- worst case
- preprocessing
- improved algorithm
- times faster
- experimental evaluation
- optimal solution
- neural network
- np hard
- dynamic programming
- detection method
- expectation maximization
- theoretical analysis
- noisy data
- tree structure
- segmentation algorithm
- linear programming
- data structure
- computational complexity
- cost function
- k means
- supervised learning
- optimization algorithm
- objective function
- training examples
- probabilistic model
- computational cost
- reinforcement learning
- decision trees
- convergence rate