Pattern Denoising in Molecular Associative Memory using Pairwise Markov Random Field Models

TL;DR

This paper introduces a molecular associative memory model using Pairwise Markov Random Fields that learns, stores, and denoises patterns with high accuracy, mimicking human memory content-addressability through DNA-based operations.

Contribution

It presents a novel in silico molecular model for pattern learning and denoising using PMRF, demonstrating effective noise reduction and pattern retrieval in DNA computation frameworks.

Findings

Low mean squared error (<0.014) up to 30% noise

Effective pattern denoising demonstrated in simulations

Content-addressable memory functionality achieved

Abstract

We propose an in silico molecular associative memory model for pattern learning, storage and denoising using Pairwise Markov Random Field (PMRF) model. Our PMRF-based molecular associative memory model extracts locally distributed features from the exposed examples, learns and stores the patterns in the molecular associative memory and denoises the given noisy patterns via DNA computation based operations. Thus, our computational molecular model demonstrates the functionalities of content-addressability of human memory. Our molecular simulation results show that the averaged mean squared error between the learned and denoised patterns are low (< 0.014) up to 30% of noise.