20240054371. SYSTEMS AND METHODS FOR INCORPORATING SUPPLEMENTAL SHAPE INFORMATION IN A LINEAR DISCRIMINANT ANALYSIS simplified abstract (Wells Fargo Bank, N.A.)
SYSTEMS AND METHODS FOR INCORPORATING SUPPLEMENTAL SHAPE INFORMATION IN A LINEAR DISCRIMINANT ANALYSIS
Organization Name
Inventor(s)
Yaoguo Xie of Charlotte NC (US)
Xindong Wang of Dayton MD (US)
SYSTEMS AND METHODS FOR INCORPORATING SUPPLEMENTAL SHAPE INFORMATION IN A LINEAR DISCRIMINANT ANALYSIS - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240054371 titled 'SYSTEMS AND METHODS FOR INCORPORATING SUPPLEMENTAL SHAPE INFORMATION IN A LINEAR DISCRIMINANT ANALYSIS
Simplified Explanation
The patent application describes a method for training a lattice linear discriminant analysis (lattice-LDA) using shape constraints for each feature in a training dataset.
- Training dataset received by communications hardware
- Set of shape constraints selected for each feature in the training dataset
- Lattice-LDA trained using training dataset and selected shape constraints
- Lattice-LDA generated based on additive form of nonlinear functions
- Training generates a shape-restricted hyperplane defining a decision boundary between two classes of data points
---
- Potential Applications
- Pattern recognition
- Image classification
- Speech recognition
- Problems Solved
- Improved accuracy in classification tasks
- Better separation of data points in high-dimensional space
- Benefits
- Enhanced performance in machine learning tasks
- More robust decision boundaries
- Increased efficiency in data analysis
Original Abstract Submitted
systems, apparatuses, methods, and computer program products are disclosed for training a lattice linear discriminant analysis (lattice-lda). an example method includes receiving, by communications hardware, a training dataset comprising one or more features, and selecting, by training circuitry, a set of shape constraints, the set of shape constraints including a shape constraint for each feature in the training dataset. the example method further includes training, by the training circuitry, the lattice-lda using the training dataset and the selected set of shape constraints, where the lattice-lda is generated based on an additive form of a plurality of nonlinear functions, and training the lattice-lda generates a shape-restricted hyperplane that defines a decision boundary separating a first class of data points in the training dataset from a second class of data points in the training dataset.
