Learning Vector Quantization
(Redirected from LVQ)
Jump to navigation
Jump to search
A Learning Vector Quantization is a supervised classification algorithm that uses prototype vectors to classify input data through vector quantization techniques.
- AKA: LVQ Algorithm, LVQ Classification.
- Context:
- It can typically learn prototype vectors from labeled training data through iterative updates.
- It can adjust prototype positions by moving them closer to correctly classified samples and away from misclassified ones.
- It can range from being a Simple LVQ Algorithm to being an Advanced LVQ Algorithm, depending on its update rule complexity.
- It can support both binary classification tasks and multi class classification tasks.
- It can maintain a set of prototype vectors for each target class.
- It can achieve classification performance comparable to other supervised learning algorithms while maintaining interpretable prototypes.
- ...
- Examples:
- LVQ Implementations, such as:
- LVQ1 Algorithm for basic prototype learning.
- OLVQ1 Algorithm with optimized learning rates.
- LVQ2 Algorithm with enhanced decision boundary optimization.
- LVQ3 Algorithm for improved convergence behavior.
- LVQ Applications, such as:
- Pattern Recognition Systems using LVQ classifiers.
- Medical Diagnosis Systems leveraging LVQ classification.
- ...
- LVQ Implementations, such as:
- Counter-Examples:
- K Means Clustering Algorithm, which performs unsupervised learning without using class labels.
- K Nearest Neighbors Algorithm, which stores all training examples rather than learning prototypes.
- See: Vector Quantization, Prototype Based Learning, Supervised Learning Algorithm, Statistical Classification.
References
2015
- (Wikipedia, 2015) ⇒ http://en.wikipedia.org/wiki/Learning_vector_quantization Retrieved:2015-10-23.
- In computer science, learning vector quantization (LVQ), is a prototype-based supervised classification algorithm. LVQ is the supervised counterpart of vector quantization systems.
2011
- (Sammut & Webb, 2011) ⇒ Claude Sammut, and Geoffrey I. Webb. (2011). “Learning Vector Quantization.” In: (Sammut & Webb, 2011) p.594