Pattern Recognition - Neural Networks

Introduction, objectives and importance of pattern recognition. Arrests and incidents. Standards and characteristics ,. classes and gatherings. DIANA-tive Standards description. Equality and Similarity Standards. Distances and inner products. Variance Table. Determining Concentration and Classes. Training with and without supervisor. Classification and Classifiers. Linear discriminant function. Linear classifiers, perceptron neural networks. Nonlinear classification problems. Neural networks back propagation. Static methods Classification. Rule Decision of Vayes. Rule of the nearest neighbor. Without Supervisor Training. Determination of Concentration. Process chain. Self-organizing characteristics tables. Neural network Kohonen. Evaluation and selection of features. Principal component analysis. Training neural networks with the rule Iebb. Applications.

Objectives

Students are taught the basic concepts, mathematical models and methods in the industry. They know the challenges of space and acquire the basic foundation for further scientific and research work.

Prerequisites

no

Syllabus

Introduction, objectives and importance of pattern recognition. Arrests and incidents. Standards and characteristics ,. classes and gatherings. DIANA-tive Standards description. Equality and Similarity Standards. Distances and inner products. Variance Table. Determining Concentration and Classes. Training with and without supervisor. Classification and Classifiers. Linear discriminant function. Linear classifiers, perceptron neural networks. Nonlinear classification problems. Neural networks back propagation. Static methods Classification. Rule Decision of Vayes. Rule of the nearest neighbor. Without Supervisor Training. Determination of Concentration. Process chain. Self-organizing characteristics tables. Neural network Kohonen. Evaluation and selection of features. Principal component analysis. Training neural networks with the rule Iebb. Applications.