- Gary Marcus: deep learning a critical appraisal (PDF of paper) via Gary’s tweet, some juicy headings from the paper:
- Is deep learning approaching a wall?
- Deep learning thus far is shallow and has limited capacity for transfer
- Deep learning thus far has no natural way to deal with hierarchical structure
- Deep learning thus far cannot inherently distinguish causation from correlation
- Deep learning presumes a largely stable world, in ways that may be problematic
- Deep learning thus far works well as an approximation, but its answers often cannot be fully trusted
- What would be better?
- Read the whole thing
Leave a comment on github