Document Type

Report

Publication Date

2018

Subjects

Paired-association learning -- Evaluation, Biochemistry -- Mathematical models

Abstract

Emerging evidence suggests that biochemical networks can be modeled by exploiting their ability to learn through associative learning. This type of learning in biomolecular structures gives it a the advantage to be able to be computationally model, and condition. Associative learning in biochemical networks is a developing area of study that once understood, can further develop diagnostic applications, and be used as tools for data analysis. Although it is a open ended project the motive of this research was to find the the best method of association learning being used in current work. After reading current work three associative learning methods were presented, such models were then analyzed to see how they implemented the associative learning methods . After understanding the models, they will be evaluated by both their challenges, and highlights. Due to time constraints trails of such associative learning methods will not be performed, but the conclusion will be based off the readings and a outline of the intended evaluation of models will be included.

Description

Presentations associated with the report are available below in the Additional Files.

Persistent Identifier

https://archives.pdx.edu/ds/psu/26236

sepulveda-symposium.pdf (1781 kB)
2018 Symposium presentation

sepulveda-ignite.pdf (510 kB)
Ignite presentation

Included in

Biomedical Commons

Share

COinS