Comparative analysis of classification algorithms
2015
machine learning algorithms are widely used in classification problems. Certainly, recognition quality of algorithms is important indicator, but the ability of the algorithm to learn is more significant. In this work the learning curves experiment was performed in order to identify which of the three learning rates occur when training the machine learning algorithms: overfitting, perfect case and underfitting. Neural Network, k-Nearest Neighbors and Naive Bayes were chosen for this experiment, since their results in previous experiments were reasonable for the log data. Also this paper contains a comparative analysis of those recognition algorithms applied to the log data of Inkai uranium deposits in Kazakhstan.
Keywords:
- Supervised learning
- Active learning (machine learning)
- Semi-supervised learning
- Instance-based learning
- Online machine learning
- Wake-sleep algorithm
- Computer science
- Stability (learning theory)
- Machine learning
- Pattern recognition
- Artificial intelligence
- Weighted Majority Algorithm
- Data mining
- Learning classifier system
- Ensemble learning
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
3
References
6
Citations
NaN
KQI