Differentiable programming includes automatic differentiation (to say, perform gradient descent automatically) and relaxation (to say, turn a symbolic program into a continuous program which supports gradient descent).
Talks
topic
- Application (5)Apply Application filter
- Ethics (2)Apply Ethics filter
- Reference (1)Apply Reference filter
- Differentiable Programming (2)Apply Differentiable Programming filter
- Interpretable AI (1)Apply Interpretable AI filter
- Neuro-Symbolic Systems (2)Apply Neuro-Symbolic Systems filter
- Reinforcement Learning (2)Apply Reinforcement Learning filter
- Probabilistic Programming (4)Apply Probabilistic Programming filter
- Representation (2)Apply Representation filter
- Synthesis (11)Apply Synthesis filter
- Verification (3)Apply Verification filter
Copyright © 2024 The President and Fellows of Harvard College | Accessibility | Digital Accessibility | Report Copyright Infringement