What Can't Deep Learning Do? – Bharath Ramsundar – Entrepreneur and Scientist
rbharath.github.io · 576 words · saved by 1 readers
1/ What can’t deep learning do? Worth putting together a list of known failures to guide algorithmic development.
1/ What can’t deep learning do? Worth putting together a list of known failures to guide algorithmic development. 2/ Deep learning methods are known to fail at learning after small jitters to input. Think object recognition breaking when colors are swapped. 3/ Gradient based learning is quite slow. Takes many, many gradient descent steps to pick up patterns. Tough for high dimensional prediction. 4/ Deep learning methods are terrible at handling constraints. Not possible to find solutions satisfying constraints unlike linear programming. 5/ Training for complex models is quite unstable.…
saved by
related reading
- The Decade of Deep Learning | Leo Gaobmk.sh
- [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
- The Little Book of Deep Learningfleuret.org
- As Rocks May Think | Eric Jangevjang.com
- DeepSeek-R1arxiv.org
- Deep learning as program synthesis — LessWronglesswrong.com
- Just Ask for Generalization | Eric Jangevjang.com
- Understanding deep learning requires rethinking generalizationarxiv.org
- Deep Learning Is Hitting a Wallnautil.us
- Andrej Karpathy — AGI is still a decade awaydwarkesh.com
- A Theory of Deep Learning | Elements of a Vector Spaceelonlit.com
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugesarxiv.org