Neural Network Learning of Chemical Bond Representations in Spectral Indices and Features

• URL: http://arxiv.org/abs/2207.10530v1
• Date: Thu, 21 Jul 2022 15:11:51 GMT
• Title: Neural Network Learning of Chemical Bond Representations in Spectral Indices and Features
• Authors: Bill Basener
• Abstract summary: We show that a Neural Network trained on different vegetation classes learn to measure this difference in reflectance. We then show that a Neural Network trained on a more complex set of ten different polymer materials will learn spectral 'features' evident in the weights for the network.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper we investigate neural networks for classification in hyperspectral imaging with a focus on connecting the architecture of the network with the physics of the sensing and materials present. Spectroscopy is the process of measuring light reflected or emitted by a material as a function wavelength. Molecular bonds present in the material have vibrational frequencies which affect the amount of light measured at each wavelength. Thus the measured spectrum contains information about the particular chemical constituents and types of bonds. For example, chlorophyll reflects more light in the near-IR rage (800-900nm) than in the red (625-675nm) range, and this difference can be measured using a normalized vegetation difference index (NDVI), which is commonly used to detect vegetation presence, health, and type in imagery collected at these wavelengths. In this paper we show that the weights in a Neural Network trained on different vegetation classes learn to measure this difference in reflectance. We then show that a Neural Network trained on a more complex set of ten different polymer materials will learn spectral 'features' evident in the weights for the network, and these features can be used to reliably distinguish between the different types of polymers. Examination of the weights provides a human-interpretable understanding of the network.

Related papers

• An Interpretable Neural Network for Vegetation Phenotyping with Visualization of Trait-Based Spectral Features [0.0]
  We present an interpretable neural network trained on the UPWINS spectral library which contains spectra with rich metadata across variation in species, health, growth stage, annual variation, and environmental conditions for 13 selected indicator species and natural common background species. We show that the neurons in the network learn spectral indicators for chemical and physiological traits through visualization of the network weights, and we show how these traits are combined by the network for species identification with an accuracy around 90% on a test set.
  arXiv  Detail & Related papers  (2024-07-14T21:20:37Z)
• Real-Time Model-Based Quantitative Ultrasound and Radar [65.268245109828]
  We propose a neural network based on the physical model of wave propagation, which defines the relationship between the received signals and physical properties. Our network can reconstruct multiple physical properties in less than one second for complex and realistic scenarios.
  arXiv  Detail & Related papers  (2024-02-16T09:09:16Z)
• Quantum fluctuations in the small Fabry-Perot interferometer [77.34726150561087]
  We study the small, of the size of the order of the wavelength, interferometer with the main mode excited by a quantum field from a nano-LED or a laser. We find the field and the photon number fluctuation spectra inside and outside the interferometer. Results help the study, design, manufacture, and use small elements of quantum optical integrated circuits.
  arXiv  Detail & Related papers  (2022-12-27T10:02:25Z)
• Curvature-informed multi-task learning for graph networks [56.155331323304]
  State-of-the-art graph neural networks attempt to predict multiple properties simultaneously. We investigate a potential explanation for this phenomenon: the curvature of each property's loss surface significantly varies, leading to inefficient learning.
  arXiv  Detail & Related papers  (2022-08-02T18:18:41Z)
• Machine learning identification of organic compounds using visible light [0.0]
  Laser-based techniques are promising for autonomous compound detection because the optical response of materials encodes enough electronic and vibrational information for remote chemical identification. We develop a machine learning classifier that can accurately identify organic species based on a single-wavelength dispersive measurement in the visible spectral region, away from absorption resonances.
  arXiv  Detail & Related papers  (2022-04-06T20:55:13Z)
• The Spectral Bias of Polynomial Neural Networks [63.27903166253743]
  Polynomial neural networks (PNNs) have been shown to be particularly effective at image generation and face recognition, where high-frequency information is critical. Previous studies have revealed that neural networks demonstrate a $textitspectral bias$ towards low-frequency functions, which yields faster learning of low-frequency components during training. Inspired by such studies, we conduct a spectral analysis of the Tangent Kernel (NTK) of PNNs. We find that the $Pi$-Net family, i.e., a recently proposed parametrization of PNNs, speeds up the
  arXiv  Detail & Related papers  (2022-02-27T23:12:43Z)
• Unsupervised Spectral Unmixing For Telluric Correction Using A Neural Network Autoencoder [58.720142291102135]
  We present a neural network autoencoder approach for extracting a telluric transmission spectrum from a large set of high-precision observed solar spectra from the HARPS-N radial velocity spectrograph.
  arXiv  Detail & Related papers  (2021-11-17T12:54:48Z)
• Using quantum states of light to probe the retinal network [0.0]
  The ability of rod cells to sense a few photons has implications for understanding the capabilities of the human visual and nervous system. We investigate the fundamental metrological capabilities of different quantum states of light to probe the retina.
  arXiv  Detail & Related papers  (2021-11-05T06:26:53Z)
• Non-Photorealistic Rendering of Layered Materials: A Multispectral Approach [0.0]
  We present multispectral rendering techniques for visualizing layered materials found in biological specimens. We are the first to use acquired data from the near-infrared and ultraviolet spectra for non-photorealistic rendering (NPR)
  arXiv  Detail & Related papers  (2021-09-02T08:40:05Z)
• A Review of 1D Convolutional Neural Networks toward Unknown Substance Identification in Portable Raman Spectrometer [0.0]
  Raman spectroscopy is a powerful analytical tool with applications ranging from quality control to cutting edge biomedical research. They have been adopted widely by first responders and law enforcement agencies for the field analysis of unknown substances. Field detection and identification of unknown substances with Raman spectroscopy rely heavily on the spectral matching capability of the devices on hand.
  arXiv  Detail & Related papers  (2020-06-18T14:28:00Z)
• Spectrum Translation for Cross-Spectral Ocular Matching [59.17685450892182]
  Cross-spectral verification remains a big issue in biometrics, especially for the ocular area. We investigate the use of Conditional Adversarial Networks for spectrum translation between near infra-red and visual light images for ocular biometrics.
  arXiv  Detail & Related papers  (2020-02-14T19:30:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.