Learning and intelligence
Human cognition and machine learning face different questions about learning, generalization, and goals.
32 problemsMachine learning
Systems that learn from data and generalize to new situations.
Collections
Browse collectionsA few problems to explore
8 totalMechanistic interpretability
We can inspect a neural network's numbers without understanding its computation. Can explanations become reliable enough to predict and check its behavior?
AI alignment
Alignment asks how AI systems can reliably follow intended goals and constraints, including in situations different from those used in training.
Continual learning
An AI system can learn new tasks and lose skills it already had. How can it keep useful knowledge while adapting with limited memory and computation?
Out-of-distribution generalization
A model can predict well on familiar data and fail when conditions change. Which changes can it handle reliably, and how can we know?
Adversarial robustness
Carefully chosen changes to an input can fool a learned classifier. How can we provide reliable protection against a stated class of such changes?
Machine unlearning
Can a trained model efficiently remove the influence of selected training data, with credible evidence of what was removed?