Volume 8

By P. Roa. 2001

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Logic Tensor Networks for Semantic Image Interpretation (2017, background): “The area of Statistical Relational Learning (SRL), or statistical AI (StarAI), seeks to combine learning from data with symbolic knowledge in the presence of uncertainty [Wang and Domingos, 2008; Bröcheler et al., 2012; Gutmann et al., 2010; Diligenti et al., 2015; Rocktaschel et al., 2015; Ravkic e”
Concrete Problems for Autonomous Vehicle Safety: Advantages of Bayesian Deep Learning (2017, background): “Instead, we wish to evaluate probabilistic predictions of agents in continuous 2D maps, therefore we assert that log probabilities [Ziebart et al., 2008; 2009] are a better suited metric for AVs.”
Should Robots be Obedient? (2017, methodology): “If H is noisily rational (Equation 1) and β = 1, then the MLE is equivalent to Maximum Entropy IRL [Ziebart et al., 2008].”
The power of quantum neural networks (2020, background): “A common way to quantify the power of a model is by its complexity [13].”
Neuro-Symbolic = Neural + Logical + Probabilistic (2019, background): “The growing consensus that both forms of reasoning are essential to achieve true (artificial) intelligence [Kahneman, 2011] has put the quest for neural symbolic computation [Garcez et al., 2012; Garcez et al., 2015; Hammer and Hitzler, 2007] high on the research agenda.”