Parallelized Linear Classification with Volumetric Chemical Perceptrons

In this work, we introduce a new type of linear classifier that is implemented in a chemical form. We propose a novel encoding technique which simultaneously represents multiple datasets in an array of microliter-scale chemical mixtures. Parallel computations on these datasets are performed as robot...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2018-10
Main Authors: Arcadia, Christopher E, Tann, Hokchhay, Dombroski, Amanda, Ferguson, Kady, Chen, Shui Ling, Kim, Eunsuk, Rose, Christopher, Rubenstein, Brenda M, Reda, Sherief, Rosenstein, Jacob K
Format: Article
Language:English
Subjects:
Algorithms
Chemical analysis
Computing time
Data storage
Datasets
Digits
Domains
Handwriting
High performance liquid chromatography
Image classification
Mathematical analysis
Multilayers
Neural networks
Organic chemistry
Parallel processing
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this work, we introduce a new type of linear classifier that is implemented in a chemical form. We propose a novel encoding technique which simultaneously represents multiple datasets in an array of microliter-scale chemical mixtures. Parallel computations on these datasets are performed as robotic liquid handling sequences, whose outputs are analyzed by high-performance liquid chromatography. As a proof of concept, we chemically encode several MNIST images of handwritten digits and demonstrate successful chemical-domain classification of the digits using volumetric perceptrons. We additionally quantify the performance of our method with a larger dataset of binary vectors and compare the experimental measurements against predicted results. Paired with appropriate chemical analysis tools, our approach can work on increasingly parallel datasets. We anticipate that related approaches will be scalable to multilayer neural networks and other more complex algorithms. Much like recent demonstrations of archival data storage in DNA, this work blurs the line between chemical and electrical information systems, and offers early insight into the computational efficiency and massive parallelism which may come with computing in chemical domains.
ISSN:2331-8422
DOI:10.48550/arxiv.1810.05214