Codebook features: Sparse and discrete interpretability for neural networks
A Tamkin, M Taufeeque, ND Goodman - ar** from latents
to observables, and Gaussian observable distributions. We here derive a solely entropy …
to observables, and Gaussian observable distributions. We here derive a solely entropy …
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 …
with latent Dirichlet allocation (LDA) being a representative model. Recently, researchers …
Sparse coding-based transfer learning for energy disaggregation
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 …
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
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 …
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 …
and potentially redundant codes make them less interpretable and less robust to noise. On …
Manifold Contrastive Learning with Variational Lie Group Operators
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 …
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 …
sparse coding. This approach shares the same explainability advantage of sparse coding …