Inferring single-trial neural population dynamics using sequential auto-encoders
Chethan Pandarinath, Daniel J O'Shea, Jasmine Collins, Rafal Jozefowicz, Sergey D Stavisky, Jonathan C Kao, Eric M Trautmann, Matthew T Kaufman, Stephen I Ryu, Leigh R Hochberg, Jaimie M Henderson, Krishna V Shenoy, L F Abbott, David Sussillo, Chethan Pandarinath, Daniel J O'Shea, Jasmine Collins, Rafal Jozefowicz, Sergey D Stavisky, Jonathan C Kao, Eric M Trautmann, Matthew T Kaufman, Stephen I Ryu, Leigh R Hochberg, Jaimie M Henderson, Krishna V Shenoy, L F Abbott, David Sussillo
Abstract
Neuroscience is experiencing a revolution in which simultaneous recording of thousands of neurons is revealing population dynamics that are not apparent from single-neuron responses. This structure is typically extracted from data averaged across many trials, but deeper understanding requires studying phenomena detected in single trials, which is challenging due to incomplete sampling of the neural population, trial-to-trial variability, and fluctuations in action potential timing. We introduce latent factor analysis via dynamical systems, a deep learning method to infer latent dynamics from single-trial neural spiking data. When applied to a variety of macaque and human motor cortical datasets, latent factor analysis via dynamical systems accurately predicts observed behavioral variables, extracts precise firing rate estimates of neural dynamics on single trials, infers perturbations to those dynamics that correlate with behavioral choices, and combines data from non-overlapping recording sessions spanning months to improve inference of underlying dynamics.
Figures
References
- Afshar A et al. Single-trial neural correlates of arm movement preparation. Neuron 71, 555–564 (2011).
- Carnevale F, de Lafuente V, Romo R, Barak O & Parga N Dynamic Control of Response Criterion in Premotor Cortex during Perceptual Detection under Temporal Uncertainty. Neuron 86, 1067–1077 (2015).
- Churchland MM et al. Neural population dynamics during reaching. Nature (2012). doi:10.1038/nature11129
- Harvey CD, Coen P & Tank DW Choice-specific sequences in parietal cortex during a virtual-navigation decision task. Nature 484, 62–68 (2012).
- Kaufman MT, Churchland MM, Ryu SI & Shenoy KV Cortical activity in the null space: permitting preparation without movement. Nat. Neurosci 17, 440–448 (2014).
- Kobak D et al. Demixed principal component analysis of neural population data. Elife 5, (2016).
- Mante V, Sussillo D, Shenoy KV & Newsome WT Context-dependent computation by recurrent dynamics in prefrontal cortex. Nature 503, 78–84 (2013).
- Pandarinath C et al. Neural population dynamics in human motor cortex during movements in people with ALS. Elife 4, (2015).
- Sadtler PT et al. Neural constraints on learning. Nature in press, 423–426 (2014).
- Shenoy KV, Sahani M & Churchland MM Cortical control of arm movements: a dynamical systems perspective. Annu. Rev. Neurosci 36, 337–359 (2013).
- Ahrens MB et al. Brain-wide neuronal dynamics during motor adaptation in zebrafish. Nature 485, 471–477 (2012).
- Yu BM et al. Gaussian-Process Factor Analysis for Low-Dimensional Single-Trial Analysis of Neural Population Activity. J. Neurophysiol 102, 614–635 (2009).
- Zhao Y & Park IM Variational Latent Gaussian Process for Recovering Single-Trial Dynamics from Population Spike Trains. Neural Comput. 29, 1293–1316 (2017).
- Aghagolzadeh M & Truccolo W Latent state-space models for neural decoding. Conf. Proc. IEEE Eng. Med. Biol. Soc 2014, 3033–3036 (2014).
- Gao Y, Archer EW, Paninski L & Cunningham JP in Advances in Neural Information Processing Systems 29 (eds. Lee DD, Sugiyama M, Luxburg UV, Guyon I & Garnett R) 163–171 (Curran Associates, Inc., 2016). at <>
- Kao JC et al. Single-trial dynamics of motor cortex and their applications to brain-machine interfaces. Nat. Commun 6, (2015).
- Macke JH et al. Empirical models of spiking in neural populations. Advances in neural information processing systems 1350–1358 (2011).
- Linderman S et al. Bayesian Learning and Inference in Recurrent Switching Linear Dynamical Systems. Artificial Intelligence and Statistics 914–922 (2017). at <>
- Petreska B et al. in Advances in Neural Information Processing Systems 24 (eds. Shawe-Taylor J, Zemel RS, Bartlett PL, Pereira F & Weinberger KQ) 756–764 (Curran Associates, Inc., 2011). at <>
- Kato S et al. Global brain dynamics embed the motor command sequence of Caenorhabditis elegans. Cell 163, 656–669 (2015).
- Kaufman MT et al. The largest response component in motor cortex reflects movement timing but not movement type. eNeuro 3, ENEURO.0085–16.2016 (2016).
- Gao P & Ganguli S On simplicity and complexity in the brave new world of large-scale neuroscience. Curr. Opin. Neurobiol 32, 148–155 (2015).
- Kingma DP & Welling M Auto-Encoding Variational Bayes. arXiv [] (2013). at <>
- Doersch C Tutorial on Variational Autoencoders. arXiv [] (2016). at <>
- Sussillo D, Jozefowicz R, Abbott LF & Pandarinath C LFADS - Latent Factor Analysis via Dynamical Systems. arXiv (2016). at <>
- Salinas E & Abbott LF Vector reconstruction from firing rates. J. Comput. Neurosci 1, 89–107 (1994).
- Willett FR et al. Feedback control policies employed by people using intracortical brain-computer interfaces. J. Neural Eng 14, (2017).
- Turaga S et al. in Advances in Neural Information Processing Systems 26 (eds. Burges CJC, Bottou L, Welling, Ghahramani Z & Weinberger KQ) 539–547 (Curran Associates, Inc., 2013). at <>
- Nonnenmacher M, Turaga SC & Macke JH in Advances in Neural Information Processing Systems 30 (eds. Guyon I et al.) 5706–5716 (Curran Associates, Inc., 2017). at <>
- Donoghue JP, Sanes JN, Hatsopoulos NG & Gaal G Neural discharge and local field potential oscillations in primate motor cortex during voluntary movements. J Neurophysiol 79, 159–173 (1998).
- Murthy VN & Fetz EE Synchronization of neurons during local field potential oscillations in sensorimotor cortex of awake monkeys. J. Neurophysiol 76, 3968–3982 (1996).
- Fries P A mechanism for cognitive dynamics: neuronal communication through neuronal coherence. Trends Cogn. Sci 9, 474–480 (2005).
- Yuste R From the neuron doctrine to neural networks. Nat. Rev. Neurosci 16, (2015).
- Gilja V et al. Clinical translation of a high-performance neural prosthesis. Nat. Med 21, (2015).
- Pandarinath C et al. High performance communication by people with paralysis using an intracortical brain-computer interface. Elife 6, (2017).
- Sussillo D et al. A recurrent neural network for closed-loop intracortical brain-machine interface decoders. J. Neural Eng 9, 26027 (2012).
- Sussillo D, Stavisky SD, Kao JC, Ryu SI & Shenoy KV Making brain–machine interfaces robust to future neural variability. Nat. Commun 7, 13749 (2016).
- Ezzyat Y et al. Closed-loop stimulation of temporal cortex rescues functional networks and improves memory. Nat. Commun 9, 365 (2018).
- Klinger NV & Mittal S Clinical efficacy of deep brain stimulation for the treatment of medically refractory epilepsy. Clin. Neurol. Neurosurg 140, 11–25 (2016).
- Little S et al. Adaptive deep brain stimulation in advanced Parkinson disease. Ann. Neurol 449–457 (2013). doi:10.1002/ana.23951
- Rosin B et al. Closed-loop deep brain stimulation is superior in ameliorating parkinsonism. Neuron 72, 370–384 (2011).
- Williamson RS, Sahani M & Pillow JW The equivalence of information-theoretic and likelihood-based methods for neural dimensionality reduction. PLoS Comput. Biol 11, e1004141 (2015).
- Rezende DJ, Mohamed S & Wierstra D Stochastic backpropagation and approximate inference in deep generative models. in International Conference on Machine Learning, 2014 (2014).
- Gregor K, Danihelka I, Graves A, Rezende DJ & Wierstra D DRAW: A Recurrent Neural Network For Image Generation. arXiv [] (2015). at <>
- Krishnan RG, Shalit U & Sontag D Deep Kalman Filters. arXiv Prepr. arXiv1511.05121 (2015).
- Chung J, Gulcehre C, Cho K & Bengio Y Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv Prepr. arXiv1412.3555 (2014).
- Hinton GE, Srivastava N, Krizhevsky A, Sutskever I & Salakhutdinov RR Improving neural networks by preventing co-adaptation of feature detectors. arXiv Prepr. arXiv1207.0580 (2012).
- Zaremba W, Sutskever I & Vinyals O Recurrent neural network regularization. arXiv Prepr. arXiv1409.2329 (2014).
- Bowman SR et al. Generating sentences from a continuous space. Conf. Comput. Nat. Lang. Learn (2016).
- Sussillo D & Abbott LF Generating coherent patterns of activity from chaotic neural networks. Neuron 63, 544–557 (2009).
- Sussillo D, Churchland MM, Kaufman MT & Shenoy KV A neural network that finds a naturalistic solution for the production of muscle activity. Nat. Neurosci 18, 1025–1033 (2015).
- Rajan K, Harvey CD & Tank DW Recurrent Network Models of Sequence Generation and Memory. Neuron 90, 1–15 (2016).
- Chung J et al. A Recurrent Latent Variable Model for Sequential Data. in Advances in Neural Information Processing Systems (NIPS) (2015).
- Gao Y, Buesing L, Shenoy KV & Cunningham JP High-dimensional neural spike train analysis with generalized count linear dynamical systems. Adv. Neural Inf. Process. Syst 1–9 (2015). at <>
- Bayer J & Osendorfer C Learning stochastic recurrent networks. arXiv Prepr. arXiv1411.7610 (2014).
- Watter M, Springenberg J, Boedecker J & Riedmiller M Embed to control: A locally linear latent dynamics model for control from raw images. in Advances in Neural Information Processing Systems 2746–2754 (2015).
- Karl M, Soelch M, Bayer J & van der Smagt P Deep variational Bayes filters: Unsupervised learning of state space models from raw data. arXiv Prepr. arXiv1605.06432 (2016).
- Gilja V et al. A high-performance neural prosthesis enabled by control algorithm design. Nat. Neurosci 15, 1752–7 (2012).
- Maaten L van der & Hinton G Visualizing data using t-SNE. J. Mach. Learn. Res 9, 2579–2605 (2008).
- Fan JM et al. Intention estimation in brain--machine interfaces. J. Neural Eng 11, 16004 (2014).
Source: PubMed