Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations.
Atticus GeigerZhengxuan WuChristopher PottsThomas IcardNoah D. GoodmanPublished in: CLeaR (2024)
Keyphrases
- causal relationships
- cooperative
- causal models
- causal relations
- distributed environment
- distributed representations
- distributed systems
- network architecture
- neural network
- random variables
- peer to peer
- causal structure
- markov blanket
- fault tolerant
- computing environments
- variable selection
- directed acyclic graph
- multi agent
- causal discovery
- structural model
- causal bayesian networks
- bio inspired
- latent variables
- probabilistic model
- pairwise
- bayesian networks