October 1, 2018 at 8:15 pm

Math-Biology Seminar | Robust Restricted Boltzmann Machine for Small Spectral Datasets, Oct. 16

Dr. Peter de B. Harrington, portrait in office

Dr. Peter de B. Harrington

The Dynamical Systems and Mathematical Biology Seminar presents Dr. Peter Harrington discussing “A Robust Restricted Boltzmann Machine for Small Spectral Datasets” on Tuesday, Oct. 16, at 3:05 p.m. in Morton 313.

Harrington is Professor of Chemistry & Biochemistry at Ohio University.

Abstract: Many advances in modern society are due to embedded artificial intelligence. Some of these innovations are voice recognition in phones and personal assistants, image recognition for identifying faces in photos, and digital transcription of handwriting. These advances rely on deep neural networks, some of which are efficiently built with layers of restricted Boltzmann machines (RBMs). The Enhanced Zippy Restricted Boltzmann Machine (EZRBM) is an enhanced RBM that uses linear inputs and generates Bernoulli outputs.  Advantages of this algorithm are that it accommodates real-valued inputs which are typical for analytical chemistry data; it trains robustly and does not require fine-tuning of parameters; and most importantly it supports backpropagation of signals so that the mechanism of inference can be ascertained. The EZRBM has many potential applications in analytical chemistry for finding features in data. They may be used to transform data and improve the performance of classification and calibration methods that are applied to the RBM outputs. Because the goal of the RBM layer is to furnish a nonlinear transform, using a cascading network structure allows both linear and nonlinear features to be made available to subsequent chemometric methods such as partial least squares and support vector machines. Some examples will demonstrate the improvement for quantifying fat and moisture content using near-infrared spectroscopy[1]. The improvement by RBMs of the classification of spectra from botanical materials, such as Cannabis or teas, for authentication and chemotyping will be demonstrated.


[1] P.B. Harrington, Feature Expansion by a Continuous Restricted Boltzmann Machine for Near-Infrared Spectrometric Calibration, Analytica Chimica Acta. (2018) 1010 20-28 DOI: 10.1016/j.aca.2018.01.026

Leave a Reply

Your email address will not be published. Required fields are marked *