An Efficient, Parallelized Algorithm for Optimal Conditional Entropy-Based Feature Selection.
Gustavo EstrelaMarco Dimas GubitosoCarlos Eduardo FerreiraJunior BarreraMarcelo da Silva ReisPublished in: Entropy (2020)
Keyphrases
- dynamic programming
- worst case
- preprocessing
- feature selection
- optimization algorithm
- optimal solution
- np hard
- high accuracy
- globally optimal
- detection algorithm
- computationally efficient
- search space
- k means
- tree structure
- data sets
- experimental evaluation
- text classification
- clustering method
- computational cost
- segmentation algorithm
- cost function
- exhaustive search
- objective function
- computational complexity
- support vector classification
- optimal parameters
- information gain
- optimal strategy
- multi class
- particle swarm optimization
- simulated annealing
- mutual information
- probabilistic model
- significant improvement
- search algorithm
- similarity measure
- decision trees
- genetic algorithm