Abstract: Directed Causal Graphs (DAGs) capture causal relationships amongst a set of variables and they specify how interventional distributions relate to observational ones.

Abstract: We study the complexity of simulating a neural network. We simplified the model of a neural network as a directed graph $G(V,E)$, where the nodes represent the neurons.

Abstract: In the stochastic K-armed bandit problem, an agent or learner is given a set of K probability distributions (informally, `arms').

Reasoning about knowledge is an old area but much of the recent technical work goes back to David Lewis and Jaakko Hintikka.  Impetus was given in Computer Science

Abstract: Driver models are invaluable for safety validation in simulation. However, driver modeling is characterized by a high degree of uncertainty.