image/svg+xml Sozi: Your First Presentation 2015-05-10 Guillaume Savaton blind faith major un- certaintiescome from Correlation Bias in data Noisy data issues in data ? input prediction model todo: Lehrer, derauf komplizierteFormeln auf Tafelzeigt ? input prediction model major un- certainties Correlation Bias in data Noisy data issues in data observe all activationsof model observer Experiment (c) (d) (b) (a) 0.25 0.5 0.75 noise 0.0 0.5 1.0 1.5 2.0 2.5 encoding error correctly_classified yes no 13.0 34.0 89.0 233.0 rotation 0.0 0.1 0.2 0.3 0.4 0.5 0.6 encoding error correctly_classified yes no 3.0 5.0 8.0 13.0 translation (pixels) 0.0 0.2 0.4 0.6 0.8 1.0 1.2 1.4 encoding error correctly_classified yes no SCARABOTTECHNOLOGIES www.scarabot.de SCARABOTTECHNOLOGIES Dipl. Ing. (FH) Andreas Gschoßmann M.Sc andreas.gschossmann@scarabot.de T +49 941 46297630 Franz-Mayer-Str. 1, 93053 Regensburg SCARABOT TECHNOLOGIES GMBH Andreas Gschoßmann andreas.gschossmann@oth-regensburg.de T +49 941 46297630 Franz-Mayer-Str. 1, 93053 Regensburg currentlyworking on A Measure of Confidence of Artificial Neural Network Classifiers Polarisedlight light-source Prism Opticaldetectionunit Angle Intensity microfluidics surface plasmon resonance spectroscopy Photoakustik Vielen Dank! Dipl. Ing. (FH) Andreas Gschoßmann M.Sc andreas.gschossmann@oth-regensburg.de T +49 941 46297630 Franz-Mayer-Str. 1, 93053 Regensburg OTH-Regensburg >> link website << observeactivations input layer hidden layer output layer observer model autoencoder
1
  1. contact
  2. sappz - photoakustik
  3. sappz - surfaceplasmons
  4. isp
  5. scarabot
  6. latest science
  7. black box
  8. blind faith
  9. major error
  10. data issues
  11. correlation
  12. bias
  13. noise
  14. all issues
  15. head
  16. observer
  17. observer
  18. method
  19. distribution
  20. experiment
  21. mnist
  22. threshold
  23. distribution noise
  24. distribution rotation
  25. distribution rotation