Undergraduate Research & Mentoring Program

Document Type

Poster

Publication Date

2016

Subjects

Computer architecture -- Design, Neural networks (Computer science) -- Design and construction

Abstract

The goal of this work is to explore applications of reservoir computing in biomolecular computation. Reservoir computing is a unique model for representing a mapping from one instance in time to a specific output. A neural network of randomly connected neurons is linked with a single output neuron or multiple output neurons. The output neurons are capable of mapping inputs to desired outputs using adaptable algorithms. This framework is investigated by using the Python programming language and object oriented design and programming. Neurons are created in programs by bundling information like input data and attributes of the network, which utilize methods (for instance the sum of a dot product, the hyperbolic tangent function) to operate on data (e.g. arbitrary input arrays, two variable binary inputs). This work is motivated by the idea of using adaptable algorithms instead of hardcoding information to solve classification problems in biomolecular computation, such as identifying molecular information like presence of a virus.

Description

The project abstract is located below in Additional Files

Persistent Identifier

http://archives.pdx.edu/ds/psu/17823

Additional Files
matt.pdf (511 kB)
Project Abstract
Download

Share

COinS