Learning Vector
Quantization…
Manojkumar C
Machine Learning vs Deep Learning :
What is Neural Network ?
Neural Networks use the architecture of human neurons which have multiple inputs, a processing
unit, and single/multiple outputs
Types of Neural Networks:
● Perceptron
● Feed Forward Neural Network
● Multilayer Perceptron
● Convolutional Neural Network
● Radial Basis Functional Neural Network
● Recurrent Neural Network
● LSTM – Long Short-Term Memory
● Sequence to Sequence Models
● Modular Neural Network
What is Learning Vector Quantization ?
Learning Vector Quantization ( or LVQ ) is a type of Artificial Neural Network which also inspired by
biological models of neural systems.
A Nearest Neighbour method, because the unknown vector from a set of reference vectors is sought
LVQ has two layers, one is the Input layer and the other one is the Output layer.
Algorithm of Learning Vector Quantization
1. Weight initialization
2. For 1 to N number of epochs
3. Select a training example
4. Compute the winning vector
5. Update the winning vector
6. Repeat steps 3, 4, 5 for all training example.
7. Classify test sample
What LVQ does ?
The LVQ algorithm allows one to choose the number of training instances to
undergo and then learns about what those instances look like.
LVQ is a prototype-based supervised classification algorithm. LVQ is
the supervised counterpart of vector quantization systems.
Uses of the Vector Quantization :
❖ Lossy data compression
❖ Lossy data correction
❖ Pattern recognition
❖ Density estimation and clustering
❖ Mainly in biometric modalities like fingerprinting, pattern
recognition, face recognition using codebooks of desired size
THANK YOU

Learning Vector Quantization - Fresh Spar Technologies - Manojkumar C

  • 1.
  • 2.
    Machine Learning vsDeep Learning :
  • 3.
    What is NeuralNetwork ? Neural Networks use the architecture of human neurons which have multiple inputs, a processing unit, and single/multiple outputs
  • 4.
    Types of NeuralNetworks: ● Perceptron ● Feed Forward Neural Network ● Multilayer Perceptron ● Convolutional Neural Network ● Radial Basis Functional Neural Network ● Recurrent Neural Network ● LSTM – Long Short-Term Memory ● Sequence to Sequence Models ● Modular Neural Network
  • 5.
    What is LearningVector Quantization ? Learning Vector Quantization ( or LVQ ) is a type of Artificial Neural Network which also inspired by biological models of neural systems. A Nearest Neighbour method, because the unknown vector from a set of reference vectors is sought LVQ has two layers, one is the Input layer and the other one is the Output layer.
  • 6.
    Algorithm of LearningVector Quantization 1. Weight initialization 2. For 1 to N number of epochs 3. Select a training example 4. Compute the winning vector 5. Update the winning vector 6. Repeat steps 3, 4, 5 for all training example. 7. Classify test sample
  • 7.
    What LVQ does? The LVQ algorithm allows one to choose the number of training instances to undergo and then learns about what those instances look like. LVQ is a prototype-based supervised classification algorithm. LVQ is the supervised counterpart of vector quantization systems.
  • 8.
    Uses of theVector Quantization : ❖ Lossy data compression ❖ Lossy data correction ❖ Pattern recognition ❖ Density estimation and clustering ❖ Mainly in biometric modalities like fingerprinting, pattern recognition, face recognition using codebooks of desired size
  • 9.