Disentangled representation learning has been proposed as an approach to learning
general representations even in the absence of, or with limited, supervision. A good general …

A central problem in unsupervised deep learning is how to find useful representations of
high-dimensional data, sometimes called" disentanglement." Most approaches are heuristic …

Contemporary neural networks still fall short of human-level generalization, which extends
far beyond our direct experiences. In this paper, we argue that the underlying cause for this …

We develop a generalisation of disentanglement in variational autoencoders (VAEs)—
decomposition of the latent representation—characterising it as the fulfilment of two factors …

Recently there has been a significant interest in learning disentangled representations, as
they promise increased interpretability, generalization to unseen scenarios and faster …

A disentangled representation encodes information about the salient factors of variation in
the data independently. Although it is often argued that this representational format is useful …

This paper proposes a hierarchical, fine-grained and interpretable latent variable model for
prosody based on the Tacotron 2 text-to-speech model. It achieves multi-resolution …

Deep learning models struggle with compositional generalization, ie the ability to recognize
or generate novel combinations of observed elementary concepts. In hopes of enabling …

There is growing interest in concept-based models (CBMs) that combine high-performance
and interpretability by acquiring and reasoning with a vocabulary of high-level concepts. A …

High-dimensional time series are common in many domains. Since human cognition is not
optimized to work well in high-dimensional spaces, these areas could benefit from …