Sort by
Refine Your Search
-
Listed
-
Category
-
Program
-
Employer
-
Field
-
for approximate inference, probabilistic programming, Bayesian deep learning, causal inference, reinforcement learning, graph neural networks, and geometric deep learning. It comprises Jan-Willem van de Meent, who
-
Bayes factor hypothesis tests in factorial designs. What are you going to do The envisioned projects will focus on the following activities related to Bayesian inference in factorial designs: Construction
-
. Desirable Expertise in computational fluid mechanics, broadly construed. Expertise in Bayesian methodology for optimization and experiment design. Experience with equivariant neural networks. Track record
-
on the following activities related to Bayesian inference in factorial designs: Construction and elicitation of informed prior distributions; Critical assessment of default prior distributions; Organizing a many
-
, simulations, and games, which use a variety of AI technologies to learn from, collaborate with, support, or improve humans; Deep Learning for Perception: Use of deep learning algorithms for computer vision
-
for differentiating effectful programs such as gradient estimation of probabilistic programs, implicit function differentiation, compositional Bayesian inference techniques); analyzing what is required (e.g., choice
-
from, collaborate with, support, or improve humans; Deep Learning for Perception: Use of deep learning algorithms for computer vision, image and audio processing, and models of perception. The focus is
-
involve: developing new differential and probabilistic programming techniques (e.g., techniques for differentiating effectful programs such as gradient estimation of probabilistic programs, implicit