Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Value Approximation.
Marco AnconaCengiz ÖztireliMarkus H. GrossPublished in: ICML (2019)
Keyphrases
- neural network
- approximation ratio
- dynamic programming
- worst case
- computational complexity
- search space
- learning algorithm
- cost function
- preprocessing
- optimization algorithm
- artificial neural networks
- objective function
- approximation guarantees
- polynomial time approximation
- efficient computation
- approximation algorithms
- error bounds
- detection algorithm
- theoretical analysis
- expectation maximization
- probabilistic model
- computational cost
- k means