A Cookbook for Deep Continuous-Time Predictive Models

A Cookbook for Deep Continuous-Time Predictive Models

Toronto Machine Learning Series (TMLS) via YouTube Direct link

Summary

18 of 20

18 of 20

Summary

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

A Cookbook for Deep Continuous-Time Predictive Models

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

  1. 1 Intro
  2. 2 A Cookbook For Deep Continuous-Time Predictive Models
  3. 3 Motivation: Irregularly-timed datasets
  4. 4 Simplest options
  5. 5 Ordinary Differential Equations
  6. 6 Autoregressive continuous-time
  7. 7 Limitations of RNN-based models
  8. 8 Latent variable models
  9. 9 ODE latent-variable model
  10. 10 Physionet: Predictive accuracy
  11. 11 Poisson Process Likelihoods
  12. 12 Limitations of Latent ODEs
  13. 13 Stochastic transition dynamics
  14. 14 What are SDEs good for?
  15. 15 What is "running an SDE backwards"?
  16. 16 Variational inference
  17. 17 1D Latent SDE
  18. 18 Summary
  19. 19 Related work 1
  20. 20 Related work 2

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.