Matthew J Johnson
TitleCited byYear
REDD: A public data set for energy disaggregation research
JZ Kolter, MJ Johnson
Workshop on Data Mining Applications in Sustainability (SIGKDD), San Diego …, 2011
Bayesian nonparametric hidden semi-Markov models
MJ Johnson, AS Willsky
Journal of Machine Learning Research 14 (Feb), 673-701, 2013
Composing graphical models with neural networks for structured representations and fast inference
M Johnson, DK Duvenaud, A Wiltschko, RP Adams, SR Datta
Advances in neural information processing systems, 2946-2954, 2016
Mapping sub-second structure in mouse behavior
AB Wiltschko, MJ Johnson, G Iurilli, RE Peterson, JM Katon, ...
Neuron 88 (6), 1121-1135, 2015
Elbo surgery: yet another way to carve up the variational evidence lower bound
MD Hoffman, MJ Johnson
Workshop in Advances in Approximate Bayesian Inference, NIPS 1, 2016
Stochastic variational inference for Bayesian time series models
M Johnson, A Willsky
International Conference on Machine Learning, 1854-1862, 2014
Dependent multinomial models made easy: Stick-breaking with the Pólya-Gamma augmentation
S Linderman, M Johnson, RP Adams
Advances in Neural Information Processing Systems, 3456-3464, 2015
Bayesian learning and inference in recurrent switching linear dynamical systems
S Linderman, M Johnson, A Miller, R Adams, D Blei, L Paninski
Artificial Intelligence and Statistics, 914-922, 2017
Analyzing hogwild parallel Gaussian Gibbs sampling
M Johnson, J Saunderson, A Willsky
Advances in Neural Information Processing Systems, 2715-2723, 2013
Patterns of scalable Bayesian inference
E Angelino, MJ Johnson, RP Adams
Foundations and Trends® in Machine Learning 9 (2-3), 119-247, 2016
The hierarchical Dirichlet process hidden semi-Markov model
MJ Johnson, A Willsky
arXiv preprint arXiv:1203.3485, 2012
A Bayesian nonparametric approach for uncovering rat hippocampal population codes during spatial navigation
SW Linderman, MJ Johnson, MA Wilson, Z Chen
Journal of neuroscience methods 263, 36-47, 2016
Structured VAEs: Composing probabilistic graphical models and variational autoencoders
MJ Johnson, D Duvenaud, AB Wiltschko, SR Datta, RP Adams
arXiv preprint arXiv:1603.06277 2, 2016, 2016
Autograd: Reverse-mode differentiation of native Python
D Maclaurin, D Duvenaud, M Johnson, RP Adams
ICML workshop on Automatic Machine Learning, 2015
Simple, distributed, and accelerated probabilistic programming
D Tran, MW Hoffman, D Moore, C Suter, S Vasudevan, A Radul
Advances in Neural Information Processing Systems, 7598-7609, 2018
Recurrent switching linear dynamical systems
SW Linderman, AC Miller, RP Adams, DM Blei, L Paninski, MJ Johnson
arXiv preprint arXiv:1610.08466, 2016
Solar: Deep structured latent representations for model-based reinforcement learning
M Zhang, S Vikram, L Smith, P Abbeel, MJ Johnson, S Levine
arXiv preprint arXiv:1808.09105, 2018
The yeast INO80 complex operates as a tunable DNA length-sensitive switch to regulate nucleosome sliding
CY Zhou, SL Johnson, LJ Lee, AD Longhurst, SL Beckwith, MJ Johnson, ...
Molecular cell 69 (4), 677-688. e9, 2018
Bayesian time series models and scalable inference
MJ Johnson
Massachusetts Institute of Technology, 2014
SOLAR: deep structured representations for model-based reinforcement learning
M Zhang, S Vikram, L Smith, P Abbeel, M Johnson, S Levine
The system can't perform the operation now. Try again later.
Articles 1–20