Representation Learning

Overlooked Implications of the Reconstruction Loss for VAE Disentanglement
Learning disentangled representations with variational autoencoders (VAEs) is often attributed to the regularisation component of the …
PDF Cite Supplementary Material
On The Specialization of Neural Modules
A number of machine learning models have been proposed with the goal of achieving systematic generalization: the ability to reason …
PDF Cite
Accounting for the Sequential Nature of States to Learn Representations in Reinforcement Learning
In this work, we investigate the properties of data that cause popular representation learning approaches to fail. In particular, we …
PDF Cite