(·)† denotes equal author contribution.
Preprints
- Interpretable deep learning for deconvolutional analysis of neural signals
Bahareh Tolooshams†, Sara Matias†, Hao Wu, Simona Temereanca, Naoshige Uchida, Venkatesh N. Murthy, Paul Masset, and Demba Ba
In submission
- Learning group representations in neural networks
Emmanouil Theodosis, Karim Helwani, and Demba Ba
In submission
- On the convergence of group-sparse autoencoders
Emmanouil Theodosis, Bahareh Tolooshams, Pranay Tankala, Abiy Tasissa, and Demba Ba
arXiv
[arxiv]
2024
- Discriminative reconstruction via simultaneous dense and sparse coding
Abiy Tasissa, Emmanouil Theodosis, Bahareh Tolooshams, and
Demba Ba
Transactions on Machine Learning Research, 2024
[official]
- Constructing gauge-invariant neural networks for scientific applications
Emmanouil Theodosis, Demba Ba, and Nima Dehmamy
ICML Workshop on Geometry-grounded Representation Learning and Generative Modeling, 2024
[official]
- Constructing gauge-invariant neural networks for scientific applications
Emmanouil Theodosis, Demba Ba, and Nima Dehmamy
ICML Workshop on AI for Science, 2024
[official]
2023
- K-Deep Simplex: Deep manifold learning via local dictionaries
Abiy Tasissa, Pranay Tankala, James Murphy, and Demba Ba
IEEE Transactions on Signal Processing, 2023
[official]
- SHAPER: Can you hear the shape of a jet?
Demba Ba, Akshunna Dogra, Rikab Gambhir, Abiy Tasissa, and Jesse Thaler
Journal of High Energy Physics, 2023
[official]
- Unrolled compressed blind-deconvolution
Bahareh Tolooshams, Satish Mulleti, Demba Ba, and Yonina Eldar
IEEE Transactions on Signal Processing, 2023
[official]
- Probabilistic unrolling: Scalable, inverse-free maximum likelihood estimation of latent Gaussian
models
Alexander Lin, Bahareh Tolooshams, Yves Atchadé, and Demba Ba
International Conference on Machine Learning, 2023
[paper]
- Learning silhouettes with group sparse autoencoders
Emmanouil Theodosis and Demba Ba
International Conference on Acoustics, Speech, and Signal Processing, 2023
[paper]
2022
- Learning unfolded networks with a cyclic group structure
Emmanouil Theodosis and Demba Ba
NeurIPS Workshop on Symmetry and Geometry in Neural Representations, 2022
[official]
- Sparse, geometric autoencoder models of V1
Jonathan Huml, Abiy Tasissa, and Demba Ba
NeurIPS Workshop on Symmetry and Geometry in Neural Representations, 2022
[official]
- Local geometry constraints in V1 with deep recurrent autoencoders
Jonathan Huml, Abiy Tasissa, and Demba Ba
NeurIPS Workshop on Shared Visual Representations in Human and Machine Intelligence, 2022
[paper]
- Interpretable unrolled dictionary learning networks
Bahareh Tolooshams and Demba Ba
DeepMath, 2022
[paper]
- Stable and interpretable unrolled dictionary learning
Bahareh Tolooshams and Demba Ba
Transactions on Machine Learning Research, 2022
[official]
- Covariance-free sparse Bayesian learning
Alexander Lin, Andrew Song, Berkin Bilgic, and Demba Ba
IEEE Transactions on Signal Processing, 2022
[official]
- Unsupervised sparse deconvolutional learning of features driving neural activity
Bahareh Tolooshams, Hao Wu, Naoshige Uchida, Venkatesh Murthy, Paul Masset, and Demba Ba
Computational and Systems Neuroscience, 2022
[paper]
- Bayesian sensitivity encoding enaables parameter-free, highly accelerated joint multi-contrast
reconstruction
Alexander Lin, Demba Ba, and Berkin Bilgic
Annual Meeting of the International Society of Magnetic Resonance in Medicine, 2022
- High-dimensional sparse Bayesian learning without covariance matrices
Alexander Lin, Andrew Song, Berkin Bilgic, and Demba Ba
International Conference on Acoustics, Speech, and Signal Processing, 2022
[official]
- Mixture model auto-encoders: Deep clustering through dictionary learning
Alexander Lin, Andrew Song, and Demba Ba
International Conference on Acoustics, Speech, and Signal Processing, 2022
[official]
2021
- Accelerating Bayesian compressed sensing for fast multi-contrast reconstructon
Alexander Lin, Demba Ba, and Berkin Bilgic
Annual Meeting of the International Society of Magnetic Resonance in Medicine, 2021
- Gaussian process convolutional dictionary learning
Andrew Song, Bahareh Tolooshams, and Demba Ba
IEEE Signal Processing Letters, 2021
[official][arxiv]
- Weighted $\ell_1$ on the simplex: Compressive sensing meets locality
Abiy Tasissa, Pranay Tankala, and Demba Ba
IEEE Statistical Signal Processing Workshop, 2021
[arxiv]
- PLSO: A generative framework for decomposing nonstationary timeseries into piecewise stationary
oscillatory components
Andrew Song, Demba Ba, and Emery Brown
Uncertainty in Artificial Intelligence, 2021
[arxiv]
- Unsupervised learning of a dictionary of neural impulse responses from spiking data
Bahareh Tolooshams, Hao Wu, Paul Masset, Venkatesh Murthy, and Demba Ba
Computational and Systems Neuroscience, 2021
[paper]
- A statistical framework for extracting time-varying oscillations from neural data
Andrew Song, Francisco Flores, Demba Ba, and Emery Brown
Computational and Systems Neuroscience, 2021
[paper]
- Unfolding neural networks for compressive multichannel blind deconvolution
Bahareh Tolooshams†, Satish Mulleti†, Demba Ba, and Yonina
Eldar
International Conference on Acoustics, Speech, and Signal Processing, 2021
[arxiv]
2020
- Deeply-sparse signal representations
Demba Ba
IEEE Transactions on Signal Processing, 2020
[official] [arxiv]
- Convolutional dictionary learning based auto-encoders for natural exponential-family
distributions
Bahareh Tolooshams†, Andrew Song†, Simona
Temereanca, and Demba Ba
International Conference on Machine Learning, 2020
[official] [arxiv] [code]
- Convolutional dictionary learning of stimulus from spiking data
Andrew Song†, Bahareh Tolooshams†, Simona
Temereanca, and Demba Ba
Computational and Systems Neuroscience, 2020
[paper]
- Convolutional dictionary learning with grid refinement
Andrew Song, Francisco Flores, and Demba Ba
IEEE Transactions on Signal Processing, 2020
[official] [arxiv]
- Deep residual auto-encoders for expectation maximization-inspired dictionary learning
Bahareh Tolooshams, Sourav Dey, and Demba Ba
IEEE Transactions on Neural Networks and Learning Systems, 2020
[official] [arxiv] [code]
2019
- Multitaper infinite Hidden Markov Model for EEG
Andrew Song, Leon Chlon, Hugo Soulat, John Tauber, Sandya Subramanian, Demba Ba, and Michael
Prerau
International Engineering in Medicine and Biology Conference, 2019
[official]
- Clustering time series with nonlinear dynamics: a bayesian non-parametric and particle-based
approach
Alexander Lin, Yingzhuo Zhang, Jeremy Heng, Stephen Allsop, Kay Tye, Pierre Jacob, and Demba Ba
International Conference on Artificial Intelligence and Statistics, 2019
[official] [arxiv]
- Convolutional dictionary learning in hierarchical networks
Javier Zazo, Bahareh Tolooshams, and Demba Ba
IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing,
2019
[arxiv]
- RandNet: Deep learning with compressed measurements of images
Thomas Chang†, Bahareh Tolooshams†, and Demba
Ba
IEEE International Workshop on Machine Learning and Signal Processing, 2019
[arxiv] [code]
2018
- Estimating a separably-Markov random field (SMuRF) from binary observations
Yingzhuo Zhang, Noa Malem-Shinitski, Stephen Allsop, Kay Tye, and Demba Ba
Neural Computation, 2018
[official]
[arxiv]
- Corticoamygdala transfer of socially derived information gates observational learning
Stephen Allsop, Romy Winchmann, Fergil Mills, Anthony Burgos-Robles, Chia-Jung Chang, Ada
Felix-Ortiz, Alienor Vienne, Anna Beyeler, Ehsan Izadmehrm Gordon Globerm Meghan Cum, Johanna
Stergiadou, Kavitha Anandalingham, Kathryn Farris, Praneeth Namburi, Christopher Leppla, Javier
Weddington, Edward Nieh, Anne Smith, Demba Ba, Emery Brown, and Kay Tye
Cell, 2018
[official]
- A modularized efficient framework for non-Markov time-series estimation
Gabriel Schamberg, Demba Ba, and Todd Coleman
IEEE Transactions on Signal Processing, 2018
[official] [arxiv]
- State-space multitaper time-frequency analysis
Seong-Eun Kim, Michael Behr, Demba Ba, and Emery Brown
Proceedings of the National Academy of Sciences, 2018
[official]
- Scalable convolutional dictionary learning with constrained recurrent sparse
auto-encoders
Bahareh Tolooshams, Sourav Dey, and Demba Ba
IEEE International Workshop on Machine Learning and Signal Processing, 2018
[arxiv] [code]
- A separable two-dimensional random field model of binary response data from multi-day behavioral
experiments
Noa Malem-Shinitski, Yingzhuo Zhang, Daniel Gray, Sarah Burke, Anne Smith, Carol Barnes, and Demba
Ba
Journal of Neuroscience Methods, 2018
[official]
2017
- Can you teach an old monkey a new trick?
Noa Malem-Shinitski, Yingzhuo Zhang, Daniel Gray, Sarah Burke, Anne Smith, Carol Barnes, and Demba
Ba
Computational and Systems Neuroscience, 2017
[paper]
- A two-dimensional seperable random field model of within and cross-trial neural spiking
dynamics
Yingzhuo Zhang, Noa Malem-Shinitski, Stephen Allsop, Kay Tye, and Demba Ba
Computational and Systems Neuroscience, 2017
[paper]
2016
- Efficient low-rank spectrotemporal decomposition using ADMM
Gabriel Schamberg, Demba Ba, Mark Wagner, and Todd Coleman
Statistical Signal Processing Workshop, 2016
[official]
- Physostigmine and methylphedate induce distinct arousal states during isoflurane general
anesthesia in rats
Jonathan Kenny, Jessica Chemali, Joseph Cotten, Christa Van Dort, Seong-Eun Kim, Demba Ba, Norman
Taylor, Emery Brown, and Ken Solt
Anesthesia and Analgesia, 2016
[official]
2015
- Measuring the signal-to-noise ratio of a neuron
Gabriela Czanner, Sridevi Sarma, Demba Ba, Uri Eden, Wei Wu, Emad Eskandar, Hubert Lim, Simona
Temereanca, Wendy Suzuki, and Emery Brown
Proceedings of the National Academy of Sciences, 2015
[official]
2014
- Algorithms for the analysis of ensemble neural spiking activity using simultaneous-event
multivariate point-process models
Demba Ba, Simona Temereanca, and Emery Brown
Frontiers in Computational Neuroscience, 2014
[official]
- Convergence and stability of iteratively re-weighted least squares algorithms
Demba Ba, Behtash Babadi, Patrick Purdon, and Emery Brown
IEEE Transactions in Signal Processing, 2014
[official]
- Likelihood methods for point processes with refractoriness
Luca Citi, Demba Ba, Emery Brown, and Riccardo Barbieri
Neural Computation, 2014
[official]
- Neural spike train denoising by point process re-weighted iterative smoothing
Demba Ba, Behtash Babadi, Patrick Purdon, and Emery Brown
Asilomar Conference on Signals, Systems, and Computers, 2014
[official]
- Robust spectrotemporal decomposition by iteratively reweighted least squares
Demba Ba, Behtash Babadi, Patrick Purdon, and Emery Brown
Proceedings of the National Academy of Sciences, 2014
[official]
2013
- Missing mass approximations for the partition function of stimulus driven Ising models
Robert Haslinger, Demba Ba, Ralf Galuske, Ziv Williams, and Gordon Pipa
Frontiers in Computational Neuroscience, 2013
[official]
2012
- Exact and stable recovery of sequences of signals with sparse increments via differential
$\ell_1$-minimization
Demba Ba, Behtash Babadi, Patrick Purdon, and Emery Brown
Neural Information Processing Systems, 2012
[official]
- Geometrically constrained room modeling with compact microphone arrays
Flavio Ribeiro, Dinei Florencio, Demba Ba, and Cha Zhang
IEEE Transactions on Audio, Speech, and Language Processing, 2012
[official]
2010
- L1 regularized room modeling with compact microphone arrays
Demba Ba, Flavio Ribeiro, Cha Zhang, and Dinei Florencio
International Conference on Acoustics, Speech, and Signal Processing, 2010
[official]
- Turning enemies into friends: Using reflections to improve sound source localization
Flavio Ribeiro, Demba Ba, Cha Zhang, and Dinei Florencio
International Conference Multimedia and Expo, 2010
[official]
- Using reverberation to improve range and elevation discrimination for small array sound source
localization
Flavio Ribeiro, Cha Zhang, Dinei Florencio, Demba Ba
IEEE Transactions on Audio, Speech and Language Processing, 2010
[official]
2009
- A regularized point process generalized linear model for assessing the functional connectivity in
the cat motor cortex
Zhe Chen, David Putrino, Demba Ba, Soumya Ghosh, Riccardo Barbieri, and Emery Brown
International Conference of the IEEE Engineering in Medicine and Biology Society, 2009
[official]
2008
- Maximum likelihood sound source localization and beamforming for directional microphone arrays in
distributed meetings
Cha Zhang, Dinei Florencio, Demba Ba, and Zhengyou Zhang
IEEE Transactions on Multimedia, 2008
[official]
2007
- Enhanced MVDR beamforming for arrays of directional microphones
Demba Ba, Dinei Florencio, and Cha Zhang
International Conference on Multimedia and Expo, 2007
[official]
- Integer polar coordinates for compression
Demba Ba, and Vivek Goyal
International Symposium on Information Theory, 2007
[official]
2006
- Nonlinear transform coding: Polar coordinates revisited
Demba Ba, and Vivek Goyal
Data Compression Conference, 2006
[official]