Encouraging sparsity in neural topic modeling with non-mean-field inference

J Chen, R Wang, J He, MJ Li - Joint European Conference on Machine …, 2023 - Springer
Topic modeling is a popular method for discovering semantic information from textual data,
with latent Dirichlet allocation (LDA) being a representative model. Recently, researchers …

Sparse coding-based transfer learning for energy disaggregation

S Chouchene, M Amayri, N Bouguila - Energy and Buildings, 2024 - Elsevier
Abstract Energy disaggregation, or Non-Intrusive Load Monitoring (NILM), is a technique
that predicts the consumption levels of individual appliances from only the main signal in the …

Decomposed linear dynamical systems (dlds) for learning the latent components of neural dynamics

N Mudrik, Y Chen, E Yezerets, CJ Rozell… - Journal of Machine …, 2024 - jmlr.org
Learning interpretable representations of neural dynamics at a population level is a crucial
first step to understanding how observed neural activity relates to perception and behavior …

Enforcing Sparsity on Latent Space for Robust and Explainable Representations

H Li, T Han - Proceedings of the IEEE/CVF Winter …, 2024 - openaccess.thecvf.com
Recently, dense latent variable models have shown promising results, but their distributed
and potentially redundant codes make them less interpretable and less robust to noise. On …

Manifold Contrastive Learning with Variational Lie Group Operators

K Fallah, A Helbling, KA Johnsen, CJ Rozell - arxiv preprint arxiv …, 2023 - arxiv.org
Self-supervised learning of deep neural networks has become a prevalent paradigm for
learning representations that transfer to a variety of downstream tasks. Similar to proposed …

Variational Convolutional Sparse Coding with Learned Thresholding

N Cleju - 2023 International Symposium on Signals, Circuits …, 2023 - ieeexplore.ieee.org
In this paper we extend the variational sparse coding framework to the case of convolutional
sparse coding. This approach shares the same explainability advantage of sparse coding …