Resources: All

Find a resource
  1. Imaging Sciences at the Oak Ridge National Laboratory: Identity Sciences, Advanced Manufacturing, Computational Imaging, Machine Learning, and Super Computing

    03 Jan 2019 | Online Presentations | Contributor(s): Hector J. Santos-Villalobos

    Dr. Santos takes us on the journey of working at the Oak Ridge National Laboratory as an imaging scientist. He showcases work in the areas of Identity Sciences (i.e., biometrics), Machine Learning, and Computational Imaging. Some application to discuss are coded source neutron imaging, non-ideal...

  2. ECE 695E Lecture 1: Where do data come from?

    03 Jan 2019 | Online Presentations | Contributor(s): Muhammad A. Alam

    OutlineA short history of dataAn example of small dataSmall vs. Big dataWhat to expect from the classConclusions

  3. ECE 695E Lecture 2: Collecting and Plotting Data

    03 Jan 2019 | Online Presentations | Contributor(s): Muhammad A. Alam

    OutlineReview of the traditional statistical metricsParametric vs. Nonparametric informationPreparing data for projection: Hazen formulaPreparing data for projection: Kaplan formulaConclusions

  4. ECE 695E Lecture 3: Physical and Empirical Distributions

    03 Jan 2019 | Online Presentations | Contributor(s): Muhammad A. Alam

    OutlinePhysical Vs. empirical distributionProperties of classical distribution functionMoment-based fitting of dataConclusions

  5. Unveiling Convolutional Neural Networks (CNNs) through An Interpretable Design

    03 Jan 2019 | Online Presentations | Contributor(s): C.-C. Jay Kuo

    We attempt to unveil the working principle of simple convolutional neural networks (CNNs) through a constructive, feedforward and interpretable design in this work. A CNN is simple if it is a cascade of two networks, where the first one consists of convolutional layers and the second one contains...

  6. Electro-thermal Properties of Carbon Nanotubes

    03 Jan 2019 | Papers | Contributor(s): Igor Bejenari

    A given technical report provides a short review of the existing experimental data and theoretical models related to electro-thermal properties of single-wall (SW) carbon nanotubes (CNT) and describes the temperature dependence of single- and multi-tube carbon nanotube field effect transistors...

  7. Creating Inflections: DARPA’s Electronics Resurgence Initiative

    09 Jan 2019 | Online Presentations | Contributor(s): William Chappell

  8. ECE 695FO: Fiber Optic Communiation

    14 Jan 2019 | Courses | Contributor(s): Peter Bermel

    The course will start with a refresher on the operation of key components needed for an effective fiber optic communication system, and then show how these components interact at a system level. Finally, the course will conclude with outlook for future research in extending the capabilities of...

  9. ECE 695E Lecture 6: Equation-free Scaling Theory for Design of Experiments

    09 Jan 2019 | Online Presentations | Contributor(s): Muhammad A. Alam

    Outline: Introduction Buckingham PI Theorem An Illustrative Example Why does the method work Conclusions

  10. ECE 695E Lecture 7: Bootstrap, Cross-Validation, and Goodness of Fit

    24 Jan 2019 | Online Presentations | Contributor(s): Muhammad A. Alam

    Outline Introdution Goodness of Fit: Adjusted R-square, AIC methods, etc. Cross-validation: Another way to compare models Bootstrap method to generation population properties based on sample characteristics Parametric vs. non-parametric distribution Conclusions

  11. ECE 695E Lecture 8: Statistical Design of Experiments

    18 Jan 2019 | Online Presentations | Contributor(s): Muhammad A. Alam

    Outline:Context and backgroundSingle factor and full factorial methodOrthogonal vector analysis: Taguchi/Fisher modelCorrelation in dependent parametersConclusions

  12. ECE 695E Lecture 9A: DOE and Taguchi Experiments

    09 Jan 2019 | Online Presentations | Contributor(s): Muhammad A. Alam

  13. ECE 695E Lecture 9B: DOE Analysis by ANOVA

    24 Jan 2019 | Online Presentations | Contributor(s): Muhammad A. Alam

    OutlineIntroduction to Analysis of Variance (Anova)Single factor Analysis of VarianceTwo factor AnovaGeneralized AnovaConclusions

  14. ECE 695E Lecture 10: Big Data Classification by Principal Component Analysis

    24 Jan 2019 | Online Presentations | Contributor(s): Muhammad A. Alam

    Outline Introduction Why do we need reduction in data dimension Theory of Principle Component Analysis Applications of Principle Component Analysis Conclusions

  15. ECE 695E Lecture 12: Basics of Machine Learning

    24 Jan 2019 | Online Presentations | Contributor(s): Muhammad A. Alam

    OutlineMachine learning is an algorithm for “fast” curve fittingMachine learning and classification: Example 1Machine learning and classification: Example 2 Any function can be represented by machine learning approach Conclusions

  16. ECE 695E Lecture 13: Deep Learning, Karnaugh Mapping, and Unsupervised Classification

    24 Jan 2019 | Online Presentations | Contributor(s): Muhammad A. Alam

    OutlineIntroductionA two input, single and multiple perceptron problemBackpropagation and coefficient fittingMachine learning and Karnaugh mappingOther forms of Machine Learning (Unsupervised, optical, quantum)Conclusions

  17. ECE 695E Lecture 14: Physics-based Machine Learning

    24 Jan 2019 | Online Presentations | Contributor(s): Muhammad A. Alam

    Outline Why and what of physics-based machine learning Example 1: Dropping a ball in the real world Example 2: Lake temperature distribution Approach 2: Structural Equation Modeling Conclusions

  18. ECE 695E Lecture 15: Conclusions and Outlook

    25 Jan 2019 | Online Presentations | Contributor(s): Muhammad A. Alam

    Outline Introduction Review of the lectures Conclusions

  19. Machine Learning for Materials Science: Part 1

    09 Feb 2019 | Tools | Contributor(s): Juan Carlos Verduzco Gastelum, Alejandro Strachan, Saaketh Desai

    Machine learning and data science tools applied to materials science

  20. Garment-Integrated Technologies Created Using Reactive Vapor Deposition

    10 Jan 2019 | Online Presentations | Contributor(s): Trisha Andrew

    Off-the-shelf garments, textiles and threads/yarns, can be nondestructively transformed into electronic circuit components using reactive vapor deposition. Selected technologies created using vapor-coated fibers and textiles will be described...