Abstract
Flexible Solution of a 2-layer Perceptron Optimization by its Size and Training Set Smooth Distortion Ratio for Classifying Simple-Structured Objects
Highlights
Computer vision controllers and monitors, functioning in real-time currents, work on objects of a finite set of C \{1} classes, which differ significantly from the pattern objects (POs) [1]
For cases of simple-structured objects on a monotonous background, it is useful to mathematically consider an object at the classifier’s input as a distorted pattern object (DPO), and so there is no difference anymore, but a shifted-skewed-scaled (SSS or S3) object [1, 2]
Classification of S3 objects is hard because of either slow classifiers based on hierarchical multilayered neural networks or poor-performing classifiers based on perceptrons [2, 9, 10]
Summary
Two-layer perceptrons are preferred to complex neural network classifiers when objects to be classified have a simple structure. The goal is to optimize the two-layer perceptron by its size and the ratio for classifying simple-structured objects. The performance is evaluated via ultimate-distortion classification error percentage. Based on statistical evaluations of classification error percentage at ultimate distortions, it is revealed that, while the best ratio should be between 0.01 and 0.02, and an optimal number of neurons in the hidden layer should be between 361 and 390. Even after the first 100 passes, the two-layer perceptron further-trained for extra 1190 passes by 10 times increasing distortion smoothness performs at 8.91 % of errors at ultimate distortions, which is about 45 % better than a previously known result. The stated example of achieving high-performance classification with two-layer perceptrons is a part of the common technique of statistical optimization relating to neural network classifiers.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Research Bulletin of the National Technical University of Ukraine "Kyiv Politechnic Institute"
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
