Incremental neural learning using AdaBoost
2002
An incremental learning system updates its hypotheses as new instances arrive without reexamining old instances. This paper describes our research in incremental neural learning. We developed an incremental neural learning (INL) framework that allows a neural network system to incrementally learn new knowledge from only new data without forgetting the existing knowledge. We have applied the INL to a vehicle fault diagnostics problem and our experiments showed very positive results.
Keywords:
- Types of artificial neural networks
- Active learning (machine learning)
- Machine learning
- Instance-based learning
- Deep learning
- Competitive learning
- Unsupervised learning
- Wake-sleep algorithm
- Artificial neural network
- Pattern recognition
- Artificial intelligence
- Computer science
- Learning classifier system
- Time delay neural network
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
13
References
7
Citations
NaN
KQI