ProgramMaster Logo
Conference Tools for MS&T21: Materials Science & Technology
Register as a New User
Submit An Abstract
Propose A Symposium
Presenter/Author Tools
Organizer/Editor Tools
About this Abstract
Meeting MS&T21: Materials Science & Technology
Symposium AI for Big Data Problems in Advanced Imaging, Materials Modeling and Automated Synthesis
Presentation Title Optimizing the Training of Convolutional Neural Networks for Image Segmentation
Author(s) Benjamin Provencher, Aly Badran, Jonathan Kroll, Mike Marsh
On-Site Speaker (Planned) Benjamin Provencher
Abstract Scope Recent advances in artificial intelligence (AI) have fully automated the operation of image segmentation in scientific images of many important materials samples, which was often laborious and painstaking by previous methods. But optimizing AI usage has been elusive because of the numerous parameters associated with training, in particular the question of how much training data is required. We look at training parameters for convolutional neural networks designed to segment x-ray microCT images for three different composite samples with 2, 3, and 5 material phases, respectively. Analysis of DICE performance of models trained in replicate shows the segmentation accuracy varies with the volume of provided ground-truth training data, but that the response quickly falls off. For all three samples, DICE scores of 0.95 are achieved when the volume of training data exceeds 4 megapixels. Importantly, synthetically augmented training data greatly compensates for a shortage of available natural ground-truth training data.


A Deep Generative Model for Parametric EBSD Pattern Simulation
Aluminum Alloy Design Using Physics Informed Machine Learning
De Novo Inverse Design of Nanoporous Materials by Machine Learning
Deep Learning and Uncertainty Quantification for Automated Experiments
Discovery of Novel Crystal Structures via Generative Adversarial Networks
Machine Learning for Automated Experiment in Scanning Probe and Electron Microscopy
Machine Learning Polymer Property Prediction Models with Polymers Represented as Natural Language
Now On-Demand Only: Non-iterative Deep Learning for High-fidelity Microscopic Tomography
Optimizing the Training of Convolutional Neural Networks for Image Segmentation
Prediction of Dynamic Properties of LiF and FLiBe Molten Salts with DeepPot Network Potentials
Refinements to the Production of Machine Learning Interatomic Potentials
Semantic Segmentation of Porosity in In-situ X-ray Tomography Data Using FCNs
Tuning Optoelectronic Properties of Semiconductors with First Principles Modeling and Machine Learning
Understanding the Composition–property Relationship of Glasses Using Interpretable Machine Learning

Questions about ProgramMaster? Contact