Tags: neural networks

Description

Neural networks are computing systems vaguely inspired by biological neural networks that as found in human or animal brains. Such systems "learn" to perform tasks by considering examples, generally without being programmed with task-specific rules.

All Categories (1-20 of 64)

  1. Message-Passing Neural Networks for Molecular Property Prediction Using Chemprop

    06 May 2022 | | Contributor(s):: Kevin Greenman

    Chemprop is an open-source implementation of a directed message passing neural network (D-MPNN) that has been demonstrated to be successful in predicting a variety of molecular properties, including solvation properties, optical properties, infrared spectra, and toxicity....

  2. Optical MNIST dataset

    21 Apr 2022 | | Contributor(s):: Hanyu Zheng

    Rapid advances in deep learning have led to paradigm shifts in a number of fields, from medical image analysis to autonomous systems. These advances, however, have resulted in digital neural networks with large computational requirements, resulting in high energy consumption and limitations in...

  3. Apr 13 2022

    Message-Passing Neural Networks for Molecular Property Prediction Using Chemprop

    Abstract: Chemprop is an open-source implementation of a directed message passing neural network (D-MPNN) that has been demonstrated to be successful in predicting a variety of molecular...

    https://nanohub.org/events/details/2170

  4. Chemprop Demo

    11 Apr 2022 | | Contributor(s):: Kevin Greenman

    Demo of the Chemprop message-passing neural network package for the Hands-on Data Science and Machine Learning Training Series

  5. Machine Learning in Physics

    04 Nov 2021 | | Contributor(s):: Nicolas Onofrio

    Lectures and tutorials to learn how to write machine learning programs with Python

  6. Machine Learning in Materials Science: Image Analysis Using Convolutional Neural Networks in MatCNN

    03 Nov 2021 | | Contributor(s):: Tiberiu Stan, Jim James, Nathan Pruyne, Marcus Schwarting, Jiwon Yeom, Peter Voorhees, Ben J Blaiszik, Ian Foster, Jonathan D Emery

      This course introduces fundamental concepts of artificial intelligence within the context of materials science and image segmentation. The two-week module was taught as part of a Computational Methods in Materials Science course at Northwestern University. The module is aimed at...

  7. MatSci 395 Lecture 5: MatCNN In-Class Tutorial

    01 Nov 2021 | | Contributor(s):: Tiberiu Stan

    Access MatCNN by clicking here

  8. MatSci 395 Lecture 6: How Do Convolutional Neural Networks Work?

    01 Nov 2021 | | Contributor(s):: Tiberiu Stan

  9. Machine learning for high entropy atomic properties

    26 Oct 2021 | | Contributor(s):: Mackinzie S Farnell, Zachary D McClure, Alejandro Strachan

    Explore machine learning models used to assess the variations in local atomic properties in high entropy alloys.

  10. MatSci 395 Lecture 4: Neural Network Training

    07 Oct 2021 | | Contributor(s):: Tiberiu Stan

  11. MatSci 395 Lecture 3: How Do Neural Networks Work?

    07 Oct 2021 | | Contributor(s):: Tiberiu Stan

  12. Debugging Neural Networks

    09 Sep 2021 | | Contributor(s):: Rishi P Gurnani

    The presentation will start with an overview of deep learning theory to motivate the logic in NetDebugger and end with a hands-on NetDebugger tutorial involving PyTorch, RDKit, and polymer data

  13. Debugging Neural Networks

    07 Aug 2021 | | Contributor(s):: Rishi P Gurnani

    Debug common errors in neural networks.

  14. Parsimonious Neural Networks Learn Interpretable Physical Laws

    21 Jun 2021 | | Contributor(s):: Saaketh Desai

    Machine learning methods are widely used as surrogate models in the physical sciences, but less explored is the use of machine learning to discover interpretable laws from data. This tutorial introduces parsimonious neural networks (PNNs), a combination of neural networks and evolutionary...

  15. A Hands-on Introduction to Physics-Informed Neural Networks

    16 Jun 2021 | | Contributor(s):: Ilias Bilionis, Atharva Hans

    Can you make a neural network satisfy a physical law? There are two main types of these laws: symmetries and ordinary/partial differential equations. I will focus on differential equations in this short presentation. The simplest way to bake information about a differential equation with neural...

  16. A Hands-on Introduction to Physics-Informed Neural Networks

    21 May 2021 | | Contributor(s):: Atharva Hans, Ilias Bilionis

    A Hands-on Introduction to Physics-Informed Neural Networks

  17. Apr 23 2021

    Parsimonious Neural Networks Learn Interpretable Physical Laws

    Machine learning methods are widely used as surrogate models in the physical sciences, but less explored is the use of machine learning to discover interpretable laws from data. This tutorial...

    https://nanohub.org/events/details/1974

  18. Deep Learning for Time Series Illustrated by COVID-19 Infection Studies

    04 Feb 2021 | | Contributor(s):: Geoffrey C. Fox

    We show that one can study several sets of sequences or time-series in terms of an underlying evolution operator which can be learned with a deep learning network.

  19. U-Net Convolutional Neural Networks for Image Segmentation: Application to Scanning Electron Microscopy Images of Graphene

    01 Feb 2021 | | Contributor(s):: Aagam Rajeev Shah

    This tutorial introduces you to U-Net, a popular convolutional neural network commonly developed for image segmentation in biomedicine. Using an assembled data set, you will learn how to create and train a U-Net neural network, and apply it to segment scanning electron microscopy images of...

  20. Module 5: Neural Networks for Regression and Classification

    01 Oct 2020 | | Contributor(s):: Saaketh Desai, Alejandro Strachan

    This module introduces neural networks for material science and engineering with hands-on online simulations. Neural networks are a subset of machine learning models used to learn mappings between inputs and outputs for a given dataset. Neural networks offer great flexibility and have shown...