Deep Learning of Dynamical Systems for Mechanistic Insight and Prediction in Psychiatry

Deep Learning of Dynamical Systems for Mechanistic Insight and Prediction in Psychiatry

Institute for Pure & Applied Mathematics (IPAM) via YouTube Direct link

Simple ahead prediction errors may be meaningless

23 of 32

23 of 32

Simple ahead prediction errors may be meaningless

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Deep Learning of Dynamical Systems for Mechanistic Insight and Prediction in Psychiatry

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 What is a dynamical system?
  3. 3 Attractor states in state space
  4. 4 Working memory tasks & persistent activity
  5. 5 Memory patterns as attractor states
  6. 6 Limit cycles ...
  7. 7 Limit cycles in motor behavior
  8. 8 Action/ thought sequences as "heteroclinic channels"
  9. 9 Altered dynamics in psychiatric states
  10. 10 Dynamical systems as a central layer of convergence
  11. 11 Recurrent Neural Network → time series
  12. 12 Making RNN deep in time
  13. 13 Piecewise-Linear (PL) RNN
  14. 14 Line-attractor regularization
  15. 15 Performance on ML benchmarks
  16. 16 Line-attractors and solving long-range tasks
  17. 17 Sequential MNIST benchmark
  18. 18 Generative PLRNN for dynamical systems
  19. 19 Reconstructing dynamical systems
  20. 20 Statistical inference for small data: Expectation.Maximization
  21. 21 Expectation-Maximization Algorithm
  22. 22 Statistical inference for big data: Sequential VAE & SGVB
  23. 23 Simple ahead prediction errors may be meaningless
  24. 24 Reconstructing DS benchmarks
  25. 25 Reconstructing DS: Lorenz system
  26. 26 Enforcing line attractor directions helps to capture multiple time scales
  27. 27 Inferring PLRNN from fMRI data
  28. 28 Does PLANN really capture measured dynamics?
  29. 29 Example 1. Unstable neuronal representations in schizophrenia
  30. 30 Example 2: Inference of dynamical systems from mobile data
  31. 31 Prediction of medical intervention effects
  32. 32 Take home's

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.