Guiding Physical Intuition with Neural Stethoscopes
Model interpretability and systematic, targeted model adaptation present central challenges in deep learning. In the domain of intuitive physics, we study the task of visually predicting stability of block towers with the goal of understanding and influencing the model's reasoning... (read more)
PDFTasks
Datasets
MuJoCo
Results from the Paper
Submit
results from this paper
to get state-of-the-art GitHub badges and help the
community compare results to other papers.
Methods used in the Paper
| METHOD | TYPE | |
|---|---|---|
Interpretability
|
Image Models |