Supervised training using an unsupervised approach to active learning

Neural Processing Letters

Volumn 15, Issue 3, 2002, Pages 247-260

  Engelbrecht, A P ^a   Brits, R ^a  

^a UNIVERSITY OF PRETORIA   (South Africa)

Author keywords

Active learning; Clustering; Incremental learning; Pattern informativeness; Sensitivity analysis

Indexed keywords

DATA REDUCTION; LEARNING ALGORITHMS; NEURAL NETWORKS; PATTERN RECOGNITION; SENSITIVITY ANALYSIS;

ACTIVE LEARNING;

LEARNING SYSTEMS;

EID: 0036608586     PISSN: 13704621     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1015733517815     Document Type: Article

References (17)

1. Neural network exploration using optimal experiment design
2. Improving generalization with active learning
3. Active learning with statistical models
4. Selective learning using sensitivity analysis
5. Incremental learning using sensitivity analysis
6. Active learning in multilayer perceptrons
7. A Novel objective function for improved phoneme recognition using time-delay neural networks
8. Selective training of feedforward artificial neural networks using matrix perturbation theory
9. Query-based learning applied to partially trained multilayer perceptrons
10. Information-based objective functions for active data selection
11. Selecting concise training sets from clean data
12. Dynamic pattern selection: Effectively training backpropagation neural networks
13. Dynamic pattern selection for faster learning and controlled generalization of neural networks
14. Query by committee
15. A formulation for active learning with applications to object detection
16. Accelerated learning by active example selection