Recent years have witnessed a surge in the popularity of Machine Learning (ML), applied
across diverse domains. However, progress is impeded by the scarcity of training data due …

We develop the sparse VAE for unsupervised representation learning on high-dimensional
data. The sparse VAE learns a set of latent factors (representations) which summarize the …

Understanding neural networks is challenging in part because of the dense, continuous
nature of their hidden states. We explore whether we can train neural networks to have …

The increasing availability of structured but high dimensional data has opened new
opportunities for optimization. One emerging and promising avenue is the exploration of …

Learning rich data representations from unlabeled data is a key challenge towards applying
deep learning algorithms in downstream tasks. Several variants of variational autoencoders …

There has been tremendous progress in artificial neural networks (ANNs) over the past
decade; however, the gap between ANNs and the biological brain as a learning device …

The focus of recent research has shifted from merely increasing the Deep Neural Networks
(DNNs) performance in various tasks to DNNs, which are more interpretable to humans. The …

Sparse coding strategies have been lauded for their parsimonious representations of data
that leverage low dimensional structure. However, inference of these codes typically relies …

Causal representation learning aims at identifying high-level causal variables from
perceptual data. Most methods assume that all latent causal variables are captured in the …

The lottery ticket hypothesis (LTH) has attracted attention because it can explain why over-
parameterized models often show high generalization ability. It is known that when we use …