I am presenting the PhD thesis that I have found useful and interesting
-
Bayesian Methods for Adaptive Models, David J.C. MacKay, 1992
-
Bayesian Learning for Neural Networks, Radford M. Neal, 1995
-
Variational Inference in Probabilistic Models, Neil D. Lawrence, 2000
-
Model selection in compositional spaces, Roger Grosse, 2014
-
Automatic Model Construction with Gaussian Processes, David Duvenaud, 2014
-
Uncertainty in Deep Learning, Yarin Gal, 2016
-
Automating Inference, Learning, and Design using Probabilistic Programming, Tom Rainforth, 2017
-
shaping and policy search in reinforcement learning, Andrew Y. Ng, 2003
-
Optimizing Expectations: From Deep Reinforcement Learning to Stochastic Computation Graphs, John Schulman, 2016
-
Principles of Metalevel Control, Nicholas Hay, 2016
-
Learning and the language of thought, Steven Thomas Piantadosi, 2011
-
Constructing the world: Active causal learning in cognition, Neil R. Bramley, 2017
-
Towards a unifying theory of generalization, Eric Schulz, 2017
-
Computational foundations of human social intelligence, Max Kleiman-Weiner, 2018
-
Meta-Reinforcement Learning with Episodic Recall: An Integrative Theory of Reward-Driven Learning, Samuel Ritter, 2019
-
Variational Inference & Deep Learning: A New Synthesis, Diederik P. Kingma, 2017
-
Neural Density Estimation and Likelihood-free Inference, G. Papamakarios, 2019
-
From Dependence to Causation, David Lopez-Paz, 2016
-
Out of Distribution Generalization in Machine Learning, Martin Arjovsky, 2019
-
Efficient Evolution of Neural Networks through Complexification, Kenneth O. Stanley, 2004
-
Evolution through the Search for Novelty, Joel Lehman, 2012
-
Learning to Generalize via Self-Supervised Prediction, Deepak Pathak, 2019