The Direction of Time
By M. Reichenbach, P. Morrison. 1956
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Bernhard Schölkopf
- David Lopez-Paz
- Yoshua Bengio
- Dacheng Tao
- Sergey Levine
- Trevor Darrell
- Ruslan Salakhutdinov
- Andrea Vedaldi
Citations in the corpus
- Discovering Causal Signals in Images (2016, background): “over two random variables Aand Bis consistent with any of the following three underlying causal structures: (i) Acauses B, (ii) Bcauses A, and (iii) Aand Bare both caused by an unobserved confounder C[15]. However, while the causal structure may not be identifiable in principle, it may be possible to”
- Semi-supervised learning, causality, and the conditional cluster assumption (2019, background): “ notion of intervention is at the heart of the difference between correlation and causation. While much of machine learning is concerned with using correlations between variables to make predictions, Reichenbach (1956) has argued that such correlations always result from underlying causal relationsh”
- Bayesian Artificial Intelligence (2004, background): “This key relates to Hans Reichenbach’s work on causality in The Direction of Time (1956) [233].”
- Inferring causal networks from observations and interventions (2003, background): “These functions are assumed to be local and modular (Reichenbach, 1956; Suppes, 1970), operating independently for each " family " of a state variable and its parents.”
- The Direction of Time (1962, methodology): “As a step towards advancing Boltzmann’s programme a bit further, I shall make use of Reichenbach’s “principle of the common cause” [ 19 ] to formulate a reasonable hypothesis about the initial probabilities.”
- Confirmatory composite analysis using partial least squares: setting the record straight (2020, background): “While in the reflective measurement model, it is assumed that the concept manifests itself in its measures, i.e., the measures share a common cause (Reichenbach 1956), in the causal–formative measurement model, the observable variables are assumed to cause the concept (Diamantopoulos et al.”