Publications by topic

version of March 4, 2023

[Natural Statistics] [Perception] [Other Neural Theory] [Neural Dynamics] [Neural Encoding] [Neural Decoding] [Neural Circuits] [Machine Learning] [Signal Processing]

Natural Statistics

[1]    M. Pachitariu and M. Sahani.
Learning visual motion in recurrent neural networks.
In P. Bartlett, F. C. N. Pereira, L. Bottou, C. J. C. Burges, and K. Q. Weinberger, eds., Advances in Neural Information Processing Systems, vol. 25, 2012.

[2]    P. Berkes, R. E. Turner, and M. Sahani.
A structured model of video reproduces primary visual cortical organisation.
PLoS Computational Biology, 5(9):e1000495, 2009.
doi pmc pdf.

[3]    P. Berkes, R. E. Turner, and M. Sahani.
On sparsity and overcompleteness in image models.
In J. C. Platt, D. Koller, Y. Singer, and S. Roweis, eds., Advances in Neural Information Processing Systems, vol. 20. Curran Associates, Inc., Red Hook, New York, 2008.
pdf.

[4]    J. Lücke and M. Sahani.
Maximal causes for non-linear component extraction.
Journal of Machine Learning Research, 9:1227–1267, 2008.
journal pdf.

[5]    R. E. Turner and M. Sahani.
Modeling natural sounds with modulation cascade processes.
In J. C. Platt, D. Koller, Y. Singer, and S. Roweis, eds., Advances in Neural Information Processing Systems, vol. 20. Curran Associates, Inc., Red Hook, New York, 2008.
pdf.

[6]    J. Lücke and M. Sahani.
Generalized softmax networks for non-linear component extraction.
In J. Marques de Sá, L. A. Alexandre, W. Duch, and D. Mandic., eds., Artificial Neural Networks – ICANN 2007 Proceedings, Part I, Lecture Notes in Computer Science, pp. 657–667. Springer, Berlin, 2007.
doi pdf.

[7]    R. E. Turner and M. Sahani.
A maximum-likelihood interpretation for slow feature analysis.
Neural Computation, 19(4):1022–1038, 2007.
doi.

[8]    R. E. Turner and M. Sahani.
Probabilistic amplitude demodulation.
In Independent Component Analysis and Signal Separation, Lecture Notes in Computer Science, pp. 544–551. Springer, 2007.
Best student paper award.
doi pdf.

Perception

[1]    L. K. Wenliang and M. Sahani.
A neurally plausible model for online recognition and postdiction.
In H. Wallach, H. Larochelle, A. Beygelzimer, F. d’Alché Buc, E. Fox, and R. Garnett, eds., Advances in Neural Information Processing Systems, vol. 32, pp. 9641–9652. Curran Associates, Inc., 2019.
online.

[2]    I. Lieder, V. Adam, O. Frenkel, S. Jaffe-Dax, M. Sahani, and M. Ahissar.
Perceptual bias reveals slow-updating in autism and fast-forgetting in dyslexia.
Nature Neuroscience, 22(2):256–264, 2019.
doi.

[3]    C. Chambers, S. Akram, V. Adam, C. Pelofi, M. Sahani, S. Shamma, and D. Pressnitzer.
Prior context in audition informs binding and shapes simple features.
Nature Communications, 8:15027, 2017.
doi.

[4]    E. R. Ferré, M. Sahani, and P. Haggard.
Subliminal stimulation and somatosensory signal detection.
Acta Psychologica, 170:103–111, 2016.
doi.

[5]    M. I. Garrido, M. Sahani, and R. J. Dolan.
Outlier responses reflect sensitivity to statistical structure in the human brain.
PLoS Computational Biology, 9(3):e1002999, 2013.
equal contributions.
doi pmc pdf.

[6]    L. Whiteley and M. Sahani.
Attention in a Bayesian framework.
Frontiers in Human Neuroscience, 6:100, 2012.
doi pmc pdf.

[7]    M. I. Garrido, G. R. Barnes, M. Sahani, and R. J. Dolan.
Functional evidence for a dual route to amygdala.
Current Biology, 22(2):129–134, 2012.
doi pmc.

[8]    M. I. Garrido, R. J. Dolan, and M. Sahani.
Surprise leads to noisier perceptual decisions.
i-Perception, 2(2):112–120, 2011.
doi pmc pdf.

[9]    M. B. Ahrens and M. Sahani.
Observers exploit stochastic models of sensory change to help judge the passage of time.
Current Biology, 21(3):200–206, 2011.
doi pmc pdf.

[10]    M. Sahani and L. Whiteley.
Modeling cue integration in cluttered environments.
In M. Landy, K. Körding, and J. Trommershäuser, eds., Sensory Cue Integration. Oxford University Press, 2011.
pdf.

[11]    S. Fleming, L. Whiteley, O. J. Hulme, M. Sahani, and R. J. Dolan.
Effects of category-specific costs on neural systems for perceptual decision-making.
Journal of Neurophysiology, 103:3238–3247, 2010.
doi pmc pdf.

[12]    M. B. Ahrens and M. Sahani.
Inferring elapsed time from stochastic neural processes.
In J. C. Platt, D. Koller, Y. Singer, and S. Roweis, eds., Advances in Neural Information Processing Systems, vol. 20. Curran Associates, Inc., Red Hook, New York, 2008.
Best student paper, honourable mention.
pdf.

[13]    L. Whiteley and M. Sahani.
Implicit knowledge of visual uncertainty guides decisions with asymmetric outcomes.
Journal of Vision, 8(3):2, 1–15, 2008.
doi pmc pdf.

Other Neural Theory

[1]    M. Salmasi and M. Sahani.
Learning neural codes for perceptual uncertainty.
In 2022 IEEE International Symposium on Information Theory (ISIT), pp. 2463–2468, 2022.
doi.

[2]    E. Vértes and M. Sahani.
A neurally plausible model learns successor representations in partially observable environments.
In H. Wallach, H. Larochelle, A. Beygelzimer, F. d’Alché Buc, E. Fox, and R. Garnett, eds., Advances in Neural Information Processing Systems, vol. 32, pp. 13692–13702. Curran Associates, Inc., 2019.
oral presentation.
online.

[3]    M. Sahani.
A biologically plausible algorithm for reinforcement-shaped representational learning.
In S. Thrun, L. Saul, and B. Schoelkopf, eds., Advances in Neural Information Processing Systems, vol. 16. MIT Press, Cambridge, Massachusetts, 2004.
pdf.

[4]    M. Sahani and P. Dayan.
Doubly distributional population codes: Simultaneous representation of uncertainty and multiplicity.
Neural Computation, 15(10):2255–2279, 2003.
doi pdf ps.gz.

[5]    P. Dayan, M. Sahani, and G. Deback.
Adaptation and unsupervised learning.
In S. Becker, S. Thrun, and K. Obermayer, eds., Advances in Neural Information Processing Systems, vol. 15, pp. 221–228. MIT Press, Cambridge, Massachusetts, 2003.

[6]    M. Sahani and P. Dayan.
Multiplicative modulation of bump attractors.
Technical Report GCNU TR 2000-05, Gatsby Computational Neuroscience Unit, University College, London, 2000.
pdf ps.gz.

Neural Dynamics

[1]    A. R. Galgali, M. Sahani, and V. Mante.
Residual dynamics resolves recurrent contributions to neural computation.
Nature Neuroscience, 26:326–338, 2023.
doi.

[2]    A. Chadwick, A. G. Khan, J. Poort, A. Blot, S. B. Hofer, T. D. Mrsic-Flogel, and M. Sahani.
Learning shapes cortical dynamics to enhance integration of relevant sensory input.
Neuron, 111:106–120.e10, 2023.
doi online.

[3]    L. Duncker and M. Sahani.
Dynamics on the manifold: Identifying computational dynamical activity from neural population recordings.
Current Opinion in Neurobiology, 70:163–170, 2021.
doi online.

[4]    H. Soulat, S. Keshavarzi, T. W. Margrie, and M. Sahani.
Probabilistic tensor decomposition of neural population spiking activity.
In M. Ranzato, A. Beygelzimer, Y. Dauphin, P. Liang, and J. W. Vaughan, eds., Advances in Neural Information Processing Systems, vol. 34, pp. 15969–15980. Curran Associates, Inc., 2021.
spotlight presentation.

[5]    V. M. S. Rutten, A. Bernacchia, M. Sahani, and G. Hennequin.
Non-reversible Gaussian processes for identifying latent dynamical structure in neural data.
In H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H.-T. Lin, eds., Advances in Neural Information Processing Systems, vol. 33, pp. 9622–9632. Curran Associates, Inc., 2020.
oral presentation.

[6]    L. Duncker, L. Driscoll, K. V. Shenoy, M. Sahani, and D. Sussillo.
Organizing recurrent network dynamics by task-computation to enable continual learning.
In H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H.-T. Lin, eds., Advances in Neural Information Processing Systems, vol. 33. Curran Associates, Inc., 2020.

[7]    L. Duncker, G. Bohner, J. Boussard, and M. Sahani.
Learning interpretable continuous-time models of latent stochastic dynamical systems.
In K. Chaudhuri and R. Salakhutdinov, eds., Proceedings of the 36th International Conference on Machine Learning (ICML), vol. 97 of Proceedings of Machince Learning Research, pp. 1726–1734. PMLR, Long Beach, California, USA, 09–15 Jun 2019.
pdf online.

[8]    L. Duncker and M. Sahani.
Temporal alignment and latent Gaussian process factor inference in population spike trains.
In S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett, eds., Advances in Neural Information Processing Systems, vol. 31, pp. 10465–10475. Curran Associates, Inc., 2018.
pdf online.

[9]    J. H. Macke, L. Buesing, and M. Sahani.
Estimating state and model parameters in state-space models of spike trains.
In Z. Chen, ed., Advanced State Space Methods for Neural and Clinical Data. Cambridge University Press, 2015.

[10]    M. Pachitariu, D. R. Lyamzin, M. Sahani, and N. A. Lesica.
State-dependent population coding in primary auditory cortex.
Journal of Neuroscience, 35(5):2058–2073, 2015.
doi pmc.

[11]    M. Pachitariu, B. Petreska, and M. Sahani.
Recurrent linear models of simultaneously-recorded neural populations.
In L. Bottou, C. J. C. Burges, M. Welling, Z. Ghahramani, and K. Q. Weinberger, eds., Advances in Neural Information Processing Systems, vol. 26, 2013.
spotlight presentation.

[12]    K. V. Shenoy, M. Sahani, and M. M. Churchland.
Cortical control of arm movements: A dynamical systems perspective.
Annual Review of Neuroscience, 36:337–359, 2013.
doi full text.

[13]    L. Buesing, J. H. Macke, and M. Sahani.
Spectral learning of linear dynamics from generalised-linear observations with application to neural population data.
In P. Bartlett, F. C. N. Pereira, L. Bottou, C. J. C. Burges, and K. Q. Weinberger, eds., Advances in Neural Information Processing Systems, vol. 25, 2012.
oral presentation.

[14]    L. Buesing, J. H. Macke, and M. Sahani.
Learning stable, regularised latent models of neural population dynamics.
Network: Computation in Neural Systems, 23(1–2):24–47, 2012.
doi pdf.

[15]    J. H. Macke, L. Büsing, J. P. Cunningham, B. M. Yu, K. V. Shenoy, and M. Sahani.
Empirical models of spiking in neural populations.
In J. Shawe-Taylor, R. S. Zemel, P. Bartlett, F. C. N. Pereira, and K. Q. Weinberger, eds., Advances in Neural Information Processing Systems, vol. 24, pp. 1350–1358. Curran Associates, Inc., Red Hook, New York, 2011.
oral presentation.
pdf.

[16]    B. Petreska, B. M. Yu, J. P. Cunningham, G. Santhanam, S. I. Ryu, K. V. Shenoy, and M. Sahani.
Dynamical segmentation of single trials from population neural data.
In J. Shawe-Taylor, R. S. Zemel, P. Bartlett, F. C. N. Pereira, and K. Q. Weinberger, eds., Advances in Neural Information Processing Systems, vol. 24, pp. 756–764. Curran Associates, Inc., Red Hook, New York, 2011.
pdf.

[17]    A. Afshar, G. Santhanam, B. M. Yu, S. I. Ryu, M. Sahani, and K. V. Shenoy.
Single-trial neural correlates of arm movement preparation.
Neuron, 71(3):555–564, 2011.
equal contributions.
doi pmc comment.

[18]    K. V. Shenoy, M. T. Kaufman, M. Sahani, and M. M. Churchland.
A dynamical systems view of motor preparation: Implications for neural prosthetic system design.
In A. Green, E. Chapman, J. F. Kalaska, and F. Lepore, eds., Progress in Brain Research: Enhancing Performance for Action and Perception, vol. 192, pp. 33–59. Elsevier, 2011.

[19]    M. M. Churchland, B. M. Yu, J. P. Cunningham, L. P. Sugrue, M. R. Cohen, G. S. Corrado, W. T. Newsome, A. M. Clark, P. Hosseini, B. B. Scott, D. C. Bradley, M. A. Smith, A. Kohn, J. A. Movshon, K. M. Armstrong, T. Moore, S. W. Chang, L. H. Snyder, S. G. Lisberger, N. J. Priebe, I. M. Finn, D. Ferster, S. I. Ryu, G. Santhanam, M. Sahani, and K. V. Shenoy.
Stimulus onset quenches neural variability: a widespread cortical phenomenon.
Nature Neuroscience, 13(3):369–378, 2010.
doi pdf.

[20]    B. M. Yu, J. P. Cunningham, G. Santhanam, S. I. Ryu, K. V. Shenoy, and M. Sahani.
Gaussian-process factor analysis for low-dimensional single-trial analysis of neural population activity.
Journal of Neurophysiology, 102:614–635, 2009.
equal contributions.
doi pmc pdf.

[21]    B. M. Yu, J. P. Cunningham, G. Santhanam, S. I. Ryu, K. V. Shenoy, and M. Sahani.
Gaussian-process factor analysis for low-dimensional single-trial analysis of neural population activity.
In D. Koller, D. Schuurmans, Y. Bengio, and L. Bottou, eds., Advances in Neural Information Processing Systems, vol. 21, pp. 1881–1888. Curran Associates, Inc., Red Hook, New York, 2009.
pdf.

[22]    J. P. Cunningham, B. M. Yu, K. V. Shenoy, and M. Sahani.
Inferring neural firing rates from spike trains using Gaussian processes.
In J. C. Platt, D. Koller, Y. Singer, and S. Roweis, eds., Advances in Neural Information Processing Systems, vol. 20. Curran Associates, Inc., Red Hook, New York, 2008.
spotlight presentation.
pdf.

[23]    J. P. Cunningham, K. V. Shenoy, and M. Sahani.
Fast Gaussian process methods for point process intensity estimation.
In Proceedings of the 25th International Conference on Machine Learning (ICML), pp. 192–199. Omnipress, Madison, Wisconsin, 2008.
pdf.

[24]    M. M. Churchland, B. M. Yu, M. Sahani, and K. V. Shenoy.
Techniques for extracting single-trial activity patterns from large-scale neural recordings.
Current Opinion in Neurobiology, 17(5):609–618, 2007.
doi pmc pdf.

[25]    B. M. Yu, A. Afshar, G. Santhanam, S. I. Ryu, K. V. Shenoy, and M. Sahani.
Extracting dynamical structure embedded in neural activity.
In Y. Weiss, B. Schölkopf, and J. Platt, eds., Advances in Neural Information Processing Systems, vol. 18, pp. 1545–1552. MIT Press, Cambridge, Massachusetts, 2006.
pdf.

[26]    B. Pesaran, J. S. Pezaris, M. Sahani, P. P. Mitra, and R. A. Andersen.
Temporal structure in neuronal activity during working memory in macaque parietal cortex.
Nature Neuroscience, 5(8):705–816, 2002.
doi.

Neural Encoding

[1]    T. Gothner, P. J. Gonçalves, M. Sahani, J. F. Linden, and K. J. Hildebrandt.
Sustained activation of PV+ interneurons in core auditory cortex enables robust divisive gain control for complex and naturalistic stimuli.
Cerebral Cortex, 31(5):2364–2381, 2021.
doi.

[2]    S. J. Jerjian, M. Sahani, and A. Kraskov.
Movement initiation and grasp representation in premotor and primary motor cortex mirror neurons.
eLife, 9:e54139, 2020.
doi.

[3]    A. F. Meyer, R. S. Williamson, J. F. Linden, and M. Sahani.
Models of neuronal stimulus-response functions: Elaboration, estimation, and evaluation.
Frontiers in Systems Neuroscience, 10:109, 2017.
doi online.

[4]    M. Sahani, G. Bohner, and A. Meyer.
Score-matching estimators for continuous-time point-process regression models.
In 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP), 2016.
doi pdf.

[5]    R. S. Williamson, M. B. Ahrens, J. F. Linden, and M. Sahani.
Input-specific gain modulation by local sensory context shapes cortical and thalamic responses to complex sounds.
Neuron, 91(1):467–480, 2016.
doi pmc pdf.

[6]    M. Pachitariu, D. R. Lyamzin, M. Sahani, and N. A. Lesica.
State-dependent population coding in primary auditory cortex.
Journal of Neuroscience, 35(5):2058–2073, 2015.
doi pmc.

[7]    R. S. Williamson, M. Sahani, and J. W. Pillow.
The equivalence of information-theoretic and likelihood-based methods for neural dimensionality reduction.
PLoS Computational Biology, 11(4):e1004141, 2015.
doi pmc.

[8]    M. Sahani, R. S. Williamson, M. B. Ahrens, and J. F. Linden.
Probabilistic methods for linear and multilinear models.
In D. Depirieux and M. Elhilahi, eds., Handbook of Modern Techniques in Auditory Cortex. Nova, Hauppage, NY, 2013.

[9]    G. B. Christianson, M. Sahani, and J. F. Linden.
Depth-dependent temporal response properties in core auditory cortex.
Journal of Neuroscience, 31(36):12837–12848, 2011.
doi pmc pdf.

[10]    B. Englitz, M. Ahrens, S. Tolnai, R. Rübsamen, M. Sahani, and J. Jost.
Multilinear models of single cell responses in the medial nucleus of the trapezoid body.
Network: Computation in Neural Systems, 21(1-2):91–124, 2010.
doi pdf.

[11]    M. B. Ahrens, J. F. Linden, and M. Sahani.
Nonlinearities and contextual influences in auditory cortical responses modeled with multilinear spectrotemporal methods.
Journal of Neuroscience, 28(8):1929–1942, 2008.
doi pdf.

[12]    M. B. Ahrens, L. Paninski, and M. Sahani.
Inferring input nonlinearities in neural encoding models.
Network: Computation in Neural Systems, 19(1):35–67, 2008.
doi pdf.

[13]    G. B. Christianson, M. Sahani, and J. F. Linden.
The consequences of response nonlinearities for interpretation of spectrotemporal receptive fields.
Journal of Neuroscience, 28(2):446–455, 2008.
doi.

[14]    J. F. Linden, R. C. Liu, M. Sahani, C. E. Schreiner, and M. M. Merzenich.
Spectrotemporal structure of receptive fields in areas AI and AAF of mouse auditory cortex.
Journal of Neurophysiology, 90(4):2660–2675, 2003.
doi.

[15]    M. Sahani and J. F. Linden.
Evidence optimization techniques for estimating stimulus-response functions.
In S. Becker, S. Thrun, and K. Obermayer, eds., Advances in Neural Information Processing Systems, vol. 15, pp. 301–308. MIT Press, Cambridge, Massachusetts, 2003.
pdf ps.gz.

[16]    M. Sahani and J. F. Linden.
How linear are auditory cortical responses?
In S. Becker, S. Thrun, and K. Obermayer, eds., Advances in Neural Information Processing Systems, vol. 15, pp. 109–116. MIT Press, Cambridge, Massachusetts, 2003.
oral presentation.
pdf ps.gz.

Neural Decoding

[1]    E. Trautmann, D. J. O’Shea, X. Sun, J. Marshel, A. Crow, B. Hsueh, S. Vesuna, L. Cofer, G. Bohner, W. Allen, I. Kauvar, S. Quirin, M. MacDougall, Y. Chen, M. Whitmire, C. Ramakrishnan, M. Sahani, E. Seidemann, S. I. Ryu, K. Deisseroth, and K. V. Shenoy.
Dendritic calcium signals in rhesus macaque motor cortex drive an optical brain-computer interface.
Nature Communications, 12(3689), 2021.
doi.

[2]    B. M. Yu, G. Santhanam, M. Sahani, and K. V. Shenoy.
Neural decoding for motor and communication prostheses.
In K. G. Oweiss, ed., Statistical Signal Processing for Neuroscience, pp. 219–263. Elsevier, 2010.

[3]    G. Santhanam, B. M. Yu, V. Gilja, S. I. Ryu, A. Afshar, M. Sahani, and K. V. Shenoy.
Factor-analysis methods for higher-performance neural prostheses.
Journal of Neurophysiology, 102:1315–1330, 2009.
doi pmc.

[4]    G. Santhanam, B. M. Yu, V. Gilja, S. I. Ryu, A. Afshar, M. Sahani, and K. V. Shenoy.
A factor-analysis decoder for high-performance neural prostheses.
In ICASSP’08: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, 2008, pp. 5208–11, 2008.
pdf.

[5]    B. M. Yu, J. P. Cunningham, K. V. Shenoy, and M. Sahani.
Neural decoding of movements: From linear to nonlinear trajectory models.
In Neural Information Processing – ICONIP 2007, Proceedings, Part I, Lecture Notes in Computer Science, pp. 586–595. Springer, 2008.
doi pdf.

[6]    B. M. Yu, C. Kemere, G. Santhanam, A. Afshar, S. I. Ryu, T. H. Meng, M. Sahani, and K. V. Shenoy.
Mixture of trajectory models for neural decoding of goal-directed movements.
Journal of Neurophysiology, 97(5):3763–3780, 2007.
equal contributions.
doi pmc pdf.

[7]    B. M. Yu, K. V. Shenoy, and M. Sahani.
Expectation propagation for inference in non-linear dynamical models with Poisson observations.
In Proceedings of the Nonlinear Statistical Signal Processing Workshop. IEEE, 2006.
pdf.

[8]    C. Kemere, M. Sahani, and T. Meng.
Robust neural decoding of reaching movements for prosthetic systems.
In Proceedings of the 25th Annual International Conference of the IEEE EMBS, vol. 3, pp. 2079–2082, 2003.
pdf.

Neural Circuits

[1]    J. Poort, K. A. Wilmes, A. Blot, A. Chadwick, M. Sahani, C. Clopath, T. D. Mrsic-Flogel, S. B. Hofer, and A. G. Khan.
Learning and attention increase visual response selectivity through distinct mechanisms.
Neuron, 110(4):686–697, 2022.
doi online.

[2]    T. Gothner, P. J. Gonçalves, M. Sahani, J. F. Linden, and K. J. Hildebrandt.
Sustained activation of PV+ interneurons in core auditory cortex enables robust divisive gain control for complex and naturalistic stimuli.
Cerebral Cortex, 31(5):2364–2381, 2021.
doi.

[3]    A. Khan, J. Poort, A. Chadwick, A. Blot, M. Sahani, T. D. Mrsic-Flogel, and S. B. Hofer.
Distinct learning-induced changes in stimulus selectivity and interactions of GABAergic interneuron classes in visual cortex.
Nature Neuroscience, 21:851–859, 2018.
doi.

[4]    C. Stringer, M. Pachitariu, N. A. Steinmetz, M. Okun, P. Bartho, K. D. Harris, M. Sahani, and N. A. Lesica.
Inhibitory control of correlated intrinsic variability in cortical networks.
eLife, 5:e19695, 2016.
doi online.

[5]    J. Poort, A. G. Khan, M. Pachitariu, A. Nemri, I. Orsolic, J. Krupic, M. Bauza, M. Sahani, G. B. Keller, T. D. Mrsic-Flogel, and S. B. Hofer.
Learning enhances sensory and multiple non-sensory representations in primary visual cortex.
Neuron, 86(6):1478–1490, 2015.
doi pmc.

Machine Learning

[1]    W. I. Walker*, H. Soulat*, C. Yu, and M. Sahani.
Unsupervised representation learning with recognition-parametrised probabilistic models.
In Artificial Intelligence and Statistics (AISTATS), vol. 206 of Proceedings of Machince Learning Research, 2023.
* equal contributions.
pdf.

[2]    T. Moskovitz, T.-C. Kao, M. Sahani, and M. Botvinick.
Minimum description length control.
In International Conference on Learning Representations (ICLR), 2023.

[3]    Y. Matsuo, Y. LeCun, M. Sahani, D. Precup, D. Silver, M. Sugiyama, E. Uchibe, and J. Morimoto.
Deep learning, reinforcement learning, and world models.
Neural Networks, 152:267–275, 2022.
doi.

[4]    T. Moskovitz, S. R. Wilson, and M. Sahani.
A first-occupancy representation for reinforcement learning.
In International Conference on Learning Representations (ICLR), 2022.

[5]    C. Yu, H. Soulat, N. Burgess, and M. Sahani.
Structured recognition for generative models with explaining away.
In Advances in Neural Information Processing Systems, vol. 35, 2022.
online.

[6]    H. Soulat, S. Keshavarzi, T. W. Margrie, and M. Sahani.
Probabilistic tensor decomposition of neural population spiking activity.
In M. Ranzato, A. Beygelzimer, Y. Dauphin, P. Liang, and J. W. Vaughan, eds., Advances in Neural Information Processing Systems, vol. 34, pp. 15969–15980. Curran Associates, Inc., 2021.
spotlight presentation.

[7]    V. M. S. Rutten, A. Bernacchia, M. Sahani, and G. Hennequin.
Non-reversible Gaussian processes for identifying latent dynamical structure in neural data.
In H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H.-T. Lin, eds., Advances in Neural Information Processing Systems, vol. 33, pp. 9622–9632. Curran Associates, Inc., 2020.
oral presentation.

[8]    L. Duncker, L. Driscoll, K. V. Shenoy, M. Sahani, and D. Sussillo.
Organizing recurrent network dynamics by task-computation to enable continual learning.
In H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H.-T. Lin, eds., Advances in Neural Information Processing Systems, vol. 33. Curran Associates, Inc., 2020.

[9]    L. K. Wenliang, T. Moskovitz, H. Kanagawa, and M. Sahani.
Amortised learning by wake-sleep.
In Proceedings of the 37th International Conference on Machine Learning (ICML), vol. 98 of Proceedings of Machince Learning Research. PMLR, 2020.

[10]    R. Singh, M. Sahani, and A. Gretton.
Kernel instrumental variable regression.
In H. Wallach, H. Larochelle, A. Beygelzimer, F. d’Alché Buc, E. Fox, and R. Garnett, eds., Advances in Neural Information Processing Systems, vol. 32, pp. 4595–4607. Curran Associates, Inc., 2019.
oral presentation.
online.

[11]    L. Duncker, G. Bohner, J. Boussard, and M. Sahani.
Learning interpretable continuous-time models of latent stochastic dynamical systems.
In K. Chaudhuri and R. Salakhutdinov, eds., Proceedings of the 36th International Conference on Machine Learning (ICML), vol. 97 of Proceedings of Machince Learning Research, pp. 1726–1734. PMLR, Long Beach, California, USA, 09–15 Jun 2019.
pdf online.

[12]    L. Duncker and M. Sahani.
Temporal alignment and latent Gaussian process factor inference in population spike trains.
In S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett, eds., Advances in Neural Information Processing Systems, vol. 31, pp. 10465–10475. Curran Associates, Inc., 2018.
pdf online.

[13]    E. Vértes and M. Sahani.
Flexible and accurate inference and learning for deep generative models.
In S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett, eds., Advances in Neural Information Processing Systems, vol. 31, pp. 4169–4178. Curran Associates, Inc., 2018.
pdf online.

[14]    L. Douglas, I. Zarov, K. Gourgoulias, C. Lucas, C. Hart, A. Baker, M. Sahani, Y. Perov, and S. Johri.
A universal marginalizer for amortized inference in generative models.
In NIPS 2017 Workshop on Advances in Approximate Bayesian Inference, 2017.
online.

[15]    E. Vértes and M. Sahani.
Learning doubly intractable latent variable models via score matching.
In Advances in Approximate Bayesian Inference, NIPS 2016 Workshop, 2016.
pdf.

[16]    M. Sahani, G. Bohner, and A. Meyer.
Score-matching estimators for continuous-time point-process regression models.
In 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP), 2016.
doi pdf.

[17]    V. Adam, J. Hensman, and M. Sahani.
Scalable transformed additive signal decomposition by non-conjugate Gaussian process inference.
In 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP), 2016.
doi pdf.

[18]    G. Bohner and M. Sahani.
Convolutional higher order matching pursuit.
In 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP), 2016.
doi pdf.

[19]    M. Park, W. Jitkrittum, A. Qamar, Z. Szabó, L. Buesing, and M. Sahani.
Bayesian manifold learning: The locally linear latent variable model.
In C. Cortes, N. D. Lawrence, D. D. Lee, M. Sugiyama, and R. Garnett, eds., Advances in Neural Information Processing Systems, vol. 28, pp. 154–162. Curran Associates, Inc., 2015.
proceedings, pdf.

[20]    J. H. Macke, L. Buesing, and M. Sahani.
Estimating state and model parameters in state-space models of spike trains.
In Z. Chen, ed., Advanced State Space Methods for Neural and Clinical Data. Cambridge University Press, 2015.

[21]    M. Henniges, R. Turner, M. Sahani, J. Eggert, and J. Lücke.
Efficient occlusive components analysis.
Journal of Machine Learning Research, 15:2689–2722, 2014.
journal pdf.

[22]    M. Pachitariu, B. Petreska, and M. Sahani.
Recurrent linear models of simultaneously-recorded neural populations.
In L. Bottou, C. J. C. Burges, M. Welling, Z. Ghahramani, and K. Q. Weinberger, eds., Advances in Neural Information Processing Systems, vol. 26, 2013.
spotlight presentation.

[23]    M. Pachitariu, N. Petitt, H. Dagleish, A. Packer, M. Haüsser, and M. Sahani.
Extracting regions of interest from biological images with convolutional sparse block coding.
In L. Bottou, C. J. C. Burges, M. Welling, Z. Ghahramani, and K. Q. Weinberger, eds., Advances in Neural Information Processing Systems, vol. 26, 2013.

[24]    L. Buesing, J. H. Macke, and M. Sahani.
Spectral learning of linear dynamics from generalised-linear observations with application to neural population data.
In P. Bartlett, F. C. N. Pereira, L. Bottou, C. J. C. Burges, and K. Q. Weinberger, eds., Advances in Neural Information Processing Systems, vol. 25, 2012.
oral presentation.

[25]    L. Buesing, J. H. Macke, and M. Sahani.
Learning stable, regularised latent models of neural population dynamics.
Network: Computation in Neural Systems, 23(1–2):24–47, 2012.
doi pdf.

[26]    G. Mysore and M. Sahani.
Variational inference in non-negative factorial hidden Markov models for efficient audio source separation.
In Proceedings of the 29th International Conference on Machine Learning (ICML). Omnipress, Madison, WI, 2012.
pdf.

[27]    R. E. Turner and M. Sahani.
Decomposing signals into a sum of amplitude and frequency modulated sinusoids using probabilistic inference.
In ICASSP’12: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 2173–2176, 2012.
doi pdf.

[28]    R. E. Turner and M. Sahani.
Probabilistic amplitude and frequency demodulation.
In J. Shawe-Taylor, R. S. Zemel, P. Bartlett, F. C. N. Pereira, and K. Q. Weinberger, eds., Advances in Neural Information Processing Systems, vol. 24, pp. 981–989. Curran Associates, Inc., Red Hook, New York, 2011.
spotlight presentation.
pdf.

[29]    R. E. Turner and M. Sahani.
Two problems with variational expectation maximisation for time-series models.
In D. Barber, A. T. Cemgil, and S. Chiappa, eds., Bayesian Time Series Models. Cambridge University Press, 2011.
pdf.

[30]    J. Lücke, R. E. Turner, M. Sahani, and M. Henniges.
Occlusive components analysis.
In Advances in Neural Information Processing Systems, vol. 22. Curran Associates, Inc., Red Hook, New York, 2009.
pdf.

[31]    P. Berkes, R. E. Turner, and M. Sahani.
A structured model of video reproduces primary visual cortical organisation.
PLoS Computational Biology, 5(9):e1000495, 2009.
doi pmc pdf.

[32]    P. Berkes, R. E. Turner, and M. Sahani.
On sparsity and overcompleteness in image models.
In J. C. Platt, D. Koller, Y. Singer, and S. Roweis, eds., Advances in Neural Information Processing Systems, vol. 20. Curran Associates, Inc., Red Hook, New York, 2008.
pdf.

[33]    J. Lücke and M. Sahani.
Maximal causes for non-linear component extraction.
Journal of Machine Learning Research, 9:1227–1267, 2008.
journal pdf.

[34]    J. Lücke and M. Sahani.
Generalized softmax networks for non-linear component extraction.
In J. Marques de Sá, L. A. Alexandre, W. Duch, and D. Mandic., eds., Artificial Neural Networks – ICANN 2007 Proceedings, Part I, Lecture Notes in Computer Science, pp. 657–667. Springer, Berlin, 2007.
doi pdf.

[35]    R. E. Turner and M. Sahani.
A maximum-likelihood interpretation for slow feature analysis.
Neural Computation, 19(4):1022–1038, 2007.
doi.

[36]    B. M. Yu, K. V. Shenoy, and M. Sahani.
Expectation propagation for inference in non-linear dynamical models with Poisson observations.
In Proceedings of the Nonlinear Statistical Signal Processing Workshop. IEEE, 2006.
pdf.

Signal Processing

[1]    V. Adam, J. Hensman, and M. Sahani.
Scalable transformed additive signal decomposition by non-conjugate Gaussian process inference.
In 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP), 2016.
doi pdf.

[2]    G. Bohner and M. Sahani.
Convolutional higher order matching pursuit.
In 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP), 2016.
doi pdf.

[3]    R. Turner and M. Sahani.
Time-frequency analysis as probabilistic inference.
IEEE Transactions on Signal Processing, 62(23):6171–6183, 2014.
doi pdf.

[4]    G. Mysore and M. Sahani.
Variational inference in non-negative factorial hidden Markov models for efficient audio source separation.
In Proceedings of the 29th International Conference on Machine Learning (ICML). Omnipress, Madison, WI, 2012.
pdf.

[5]    R. E. Turner and M. Sahani.
Decomposing signals into a sum of amplitude and frequency modulated sinusoids using probabilistic inference.
In ICASSP’12: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 2173–2176, 2012.
doi pdf.

[6]    R. E. Turner and M. Sahani.
Probabilistic amplitude and frequency demodulation.
In J. Shawe-Taylor, R. S. Zemel, P. Bartlett, F. C. N. Pereira, and K. Q. Weinberger, eds., Advances in Neural Information Processing Systems, vol. 24, pp. 981–989. Curran Associates, Inc., Red Hook, New York, 2011.
spotlight presentation.
pdf.

[7]    R. E. Turner and M. Sahani.
Demodulation as probabilistic inference.
IEEE Transactions on Audio, Speech and Language Processing, 19(8):2398–2411, 2011.
doi pdf.

[8]    R. E. Turner and M. Sahani.
Two problems with variational expectation maximisation for time-series models.
In D. Barber, A. T. Cemgil, and S. Chiappa, eds., Bayesian Time Series Models. Cambridge University Press, 2011.
pdf.

[9]    R. E. Turner and M. Sahani.
Statistical inference for single- and multi-band probabilistic amplitude demodulation.
In ICASSP’10: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 5466–5469, 2010.
doi pdf.

[10]    R. E. Turner and M. Sahani.
Modeling natural sounds with modulation cascade processes.
In J. C. Platt, D. Koller, Y. Singer, and S. Roweis, eds., Advances in Neural Information Processing Systems, vol. 20. Curran Associates, Inc., Red Hook, New York, 2008.
pdf.

[11]    R. E. Turner and M. Sahani.
Probabilistic amplitude demodulation.
In Independent Component Analysis and Signal Separation, Lecture Notes in Computer Science, pp. 544–551. Springer, 2007.
Best student paper award.
doi pdf.

[12]    R. E. Turner and M. Sahani.
A maximum-likelihood interpretation for slow feature analysis.
Neural Computation, 19(4):1022–1038, 2007.
doi.

[13]    B. M. Yu, K. V. Shenoy, and M. Sahani.
Expectation propagation for inference in non-linear dynamical models with Poisson observations.
In Proceedings of the Nonlinear Statistical Signal Processing Workshop. IEEE, 2006.
pdf.