Learning Module Improvements

Improvements we would like to add to the learning modules.

We have a guide on customizing learning modules here.

These are the things we would like to implement:

• Use off-object observations #numsteps #multiobj
• Implement and test rapid evidence decay as form of unsupervised memory resetting
• Improve bounded evidence performance
• Use models with fewer points
• Test particle-filter-like resampling of hypothesis space
• Re-anchor hypotheses for robustness to noise and distortions
• Less dependency on first observation
• Deal with incomplete models
• Deal with moving objects
• Support scale invariance
• Improve handling of symmetry
• Use Better Priors for Hypothesis Initialization
• Learn hot spots on objects
• Include State in Models
• Include State in Hypotheses
• Event Detection to Reset Timer
• Speed Detection to Adjust Timer

Please see the instructions here if you would like to tackle one of these tasks.

---

Help Us Make This Page Better

All our docs are open-source. If something is wrong or unclear, submit a PR to fix it!

Make a Contribution

Learn how to contribute to our docs