Pattern Recognition of Saccharomyces Cerevisiae Gene Expression Using Backpropagation Training Functions That Use Gradient Derivatives Neural Network
Year: 2026
Type: conference-paper
Abstract: This paper presents a pattern recognition approach for Saccharomyces Cerevisiae using different neural network training models. Feedforward pattern recognition networks were trained to classify genes into five known cell-cycle classes of Saccharomyces Cerevisiae. The aim is to recognize patterns in different genes across five classes. The challenge is to translate sequences into functions. The objective is to identify gene expression patterns and improve functional classification using microarray data. A different training model in a neural network is used as a pattern recognition technique to determine the target classes of the five known classes. Based on the results, the CGP technique gives a good representation based on the 85.9% performance for all during training, testing, and validation using parallel processing and GPU-enabled training, and scaled conjugate gradient backpropagation gives better performance and a low error rate.
Author: Julie Ann Acebuque Salido
Institution: Aklan State University
Language: English
Subfield: Molecular Biology
Domain: Life Sciences
Open Access status: hybrid
OpenAlex ID: W7222467607