Factor-Analysis Methods for Higher-Performance Neural Prostheses
Open accessThe DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Abstract
Neural prostheses aim to provide treatment options for individuals with nervous-system disease or injury. It is necessary, however, to increase the performance of such systems before they can be clinically viable for patients with motor dysfunction. One performance limitation is the presence of correlated trial-to-trial variability that can cause neural responses to wax and wane in concert as the subject is, for example, more attentive or more fatigued. If a system does not properly account for this variability, it may mistakenly interpret such variability as an entirely different intention by the subject. We report here the design and characterization of factor-analysis (FA)–based decoding algorithms that can contend with this confound. We characterize the decoders (classifiers) on experimental data where monkeys performed both a real reach task and a prosthetic cursor task while we recorded from 96 electrodes implanted in dorsal premotor cortex. The decoder attempts to infer the underlying factors that comodulate the neurons' responses and can use this information to substantially lower error rates (one of eight reach endpoint predictions) by ≲75% (e.g., ∼20% total prediction error using traditional independent Poisson models reduced to ∼5%). We also examine additional key aspects of these new algorithms: the effect of neural integration window length on performance, an extension of the algorithms to use Poisson statistics, and the effect of training set size on the decoding accuracy of test data. We found that FA-based methods are most effective for integration windows >150 ms, although still advantageous at shorter timescales, that Gaussian-based algorithms performed better than the analogous Poisson-based algorithms and that the FA algorithm is robust even with a limited amount of training data. We propose that FA-based methods are effective in modeling correlated trial-to-trial neural variability and can be used to substantially increase overall prosthetic system performance.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Probabilistic Principal Component Analysis
Tipping, M. E., & Bishop, C. M. (1999) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/1467-9868.00196 · Cited by 3,679
Neuronal ensemble control of prosthetic devices by a human with tetraplegia
Hochberg, L. R., Serruya, M. D., Friehs, G. M., Mukand, J. A., Saleh, M., Caplan, A. H., Branner, A., Chen, D., Penn, R. D., & Donoghue, J. P. (2006) · Nature · doi:10.1038/nature04970 · Cited by 3,295 · cited 2×
“2008) and humans (e.g., Kennedy et al. 2000; Leuthardt et al. 2004; Wolpaw and McFarland 2004; Hochberg et al. 2006; Schalk et al. 2008) can learn to move computer cursors and robotic arms to various target locations simply by activating neural populations that participate in natural arm movements.”
BackgroundShadlen, M. N., & Newsome, W. T. (1998) · The Journal of Neuroscience · doi:10.1523/jneurosci.18-10-03870.1998 · Cited by 2,178 · cited 2×
“Furthermore, spike counts can sometimes be sub- or superPoisson (Churchland et al. 2006b; Shadlen and Newsome 1998).”
BackgroundLearning to control a brain–machine interface for reaching and grasping by primates
Carmena, J. M., Lebedev, M. A., Crist, R. E., O'Doherty, J. E., Santucci, D. M., Dimitrov, D. F., Patil, P. G., Henriquez, C. S., & Nicolelis, M. A. L. (2003) · PLoS Biology · doi:10.1371/journal.pbio.0000042 · Cited by 1,761 · cited 2×
“A few research groups have now demonstrated that monkeys (e.g., Taylor et al. 2002; Serruya et al. 2002; Carmena et al. 2003; Musallam et al. 2004; Santhanam et al. 2006a; Velliste et al. 2008) and humans (e.”
BackgroundCortical control of a prosthetic arm for self-feeding
Velliste, M., Perel, S., Spalding, M. C., Whitford, A. S., & Schwartz, A. B. (2008) · Nature · doi:10.1038/nature06996 · Cited by 1,591
Control of a two-dimensional movement signal by a noninvasive brain-computer interface in humans
Wolpaw, J. R., & McFarland, D. J. (2004) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0403504101 · Cited by 1,512
Coding of visual space by premotor neurons.
Graziano, M. S. A., Yap, G. S., & Gross, C. G. (1994) · Science · doi:10.1126/science.7973661 · Cited by 841
A high-performance brain–computer interface
Santhanam, G., Ryu, S. I., Yu, B. M., Afshar, A., & Shenoy, K. V. (2006) · Nature · doi:10.1038/nature04968 · Cited by 698
Self-citationCognitive Control Signals for Neural Prosthetics
Musallam, S., Corneil, B. D., Greger, B., Scherberger, H., & Andersen, R. A. (2004) · Science · doi:10.1126/science.1097938 · Cited by 663 · cited 5×
“A few research groups have now demonstrated that monkeys (e.g., Carmena et al. 2003; Musallam et al. 2004; Santhanam et al. 2006a; Serruya et al. 2002; Taylor et al. 2002; Velliste et al. 2008) and humans (e.g., Hochberg et al. 2006; Kennedy et al. 2000; Leuthardt et al. 2004; Schalk et al. 2008;…”
BackgroundMethodInfluentialVisuospatial properties of ventral premotor cortex
Graziano, M. S. A., Hu, X. T., & Gross, C. G. (1997) · Journal of Neurophysiology · doi:10.1152/jn.1997.77.5.2268 · Cited by 603
A computational perspective on the neural basis of multisensory spatial representations
Pouget, A., Deneve, S., & Duhamel, J.-R. (2002) · Nature Reviews Neuroscience · doi:10.1038/nrn914 · Cited by 413
A central source of movement variability
Churchland, M. M., Afshar, A., & Shenoy, K. V. (2006) · Neuron · doi:10.1016/j.neuron.2006.10.034 · Cited by 393 · cited 4×
“…PMd activity can depend on other behavioral aspects of movement control, including the type of grasp (Godschalk et al. 1985), the required accuracy (Gomez et al. 2000), reach curvature (Hocherman and Wise 1991), reach speed (Churchland et al. 2006a), and (to some degree) force (Riehle et al. 1994).”
BackgroundInfluentialComputational approaches to sensorimotor transformations
Pouget, A., & Snyder, L. H. (2000) · Nature Neuroscience · doi:10.1038/81469 · Cited by 357
Tanné-Gariépy, J., Rouiller, E. M., & Boussaoud, D. (2002) · Experimental Brain Research · doi:10.1007/s00221-002-1078-9 · Cited by 289
Detecting Neural-State Transitions Using Hidden Markov Models for Motor Cortical Prostheses
Kemere, C., Santhanam, G., Yu, B. M., Afshar, A., Ryu, S. I., Meng, T. H., & Shenoy, K. V. (2008) · Journal of Neurophysiology · doi:10.1152/jn.00924.2007 · Cited by 157
Self-citationToward Optimal Target Placement for Neural Prosthetic Devices
Cunningham, J. P., Yu, B. M., Gilja, V., Ryu, S. I., & Shenoy, K. V. (2008) · Journal of Neurophysiology · doi:10.1152/jn.90833.2008 · Cited by 25
Self-citation
Research works printed but not linked: 41
- 10.1152/jn.00421.2006 · DOI · Paper page
- 10.1152/jn.00438.2003 · DOI · Paper page
- 10.1523/JNEUROSCI.18-18-07411.1998 · DOI · Paper page
- 10.1523/JNEUROSCI.0959-07.2007 · DOI · Paper page
- 10.1152/jn.00307.2006 · DOI · Paper page
- 10.1523/JNEUROSCI.3762-05.2006 · DOI · Paper page
- 10.1152/jn.00995.2001 · DOI
- 10.1038/nature03005 · DOI · Paper page
- Dayan P, Abbott LF. Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems. Cambridge, MA: MIT Press, 2001.
- Dempster AP, Laird NM, Rubin DB. Maximum likelihood from incomplete data via the EM algorithm (with discussion). J R Stat Soc Ser B 39: 1–38, 1977. · DOI · Paper page
- Everitt BS. An Introduction to Latent Variable Models. London: Chapman & Hall, 1984. · DOI · Paper page
- 10.1038/nrn2258 · DOI · Paper page
- 10.1523/JNEUROSCI.02-11-01527.1982 · DOI · Paper page
- 10.1016/0166-4328(85)90070-1 · DOI · Paper page
- 10.1046/j.1460-9568.2000.00232.x · DOI
- 10.1152/jn.01245.2003 · DOI · Paper page
- 10.1007/BF00231153 · DOI · Paper page
- 10.1109/86.847815 · DOI · Paper page
- 10.2307/2346609 · DOI
- 10.1080/09548980701625173 · DOI · Paper page
- 10.1088/1741-2560/1/2/001 · DOI · Paper page
- 10.1523/JNEUROSCI.19-18-08083.1999 · DOI · Paper page
- 10.1152/jn.2000.84.1.152 · DOI · Paper page
- Ng AY, Jordan MI. On discriminative vs. generative classifiers: a comparison of logistic regression and naive Bayes. In: Advances in Neural Information Processing Systems 14, edited by Dietterich TG, Becker S, Ghahramani Z. Cambridge, MA: MIT Press, 2002, vol. 2, p. 841–848.
- 10.1162/0899766054322973 · DOI · Paper page
- Raina R, Shen Y, Ng AY, McCallum A. Classification with hybrid generative/discriminative models. In: Advances in Neural Information Processing Systems 16, edited by Thrun S, Saul LK, Schölkopf B. Cambridge, MA: MIT Press, 2004, p. 545–552.
- 10.1007/BF00241412 · DOI
- 10.1162/089976699300016674 · DOI · Paper page
- Roweis ST. EM algorithms for PCA and SPCA. In: Advances in Neural Information Processing Systems 10, edited by Jordan MI, Kearns MJ, Solla SA. Cambridge, MA: MIT Press, 1998, p. 626–632.
- 10.1088/1741-2560/5/1/008 · DOI · Paper page
- 10.1038/416141a · DOI · Paper page
- 10.1097/00001756-200303240-00013 · DOI · Paper page
- 10.1159/000022953 · DOI · Paper page
- 10.1162/089976603765202622 · DOI · Paper page
- 10.1126/science.1070291 · DOI · Paper page
- 10.1152/jn.00697.2004 · DOI · Paper page
- 10.1162/089976606774841585 · DOI · Paper page
- Wu W, Kulkarni JE, Hatsopoulos NG, Paninski L. Neural decoding of goal-directed movements using a linear statespace. In: Computational and Systems Neuroscience (COSYNE) 2008 Workshops, Salt Lake City, UT. New York: Nova Science, 2008, p. 155.
- Yu BM, Afshar A, Santhanam G, Ryu SI, Shenoy KV, Sahani M. Extracting dynamical structure embedded in neural activity. In: Advances in Neural Information Processing Systems 18, edited by Weiss Y, Schölkopf B, Platt J. Cambridge, MA: MIT Press, 2006, p. 1545–1552.
- 10.1152/jn.00482.2006 · DOI · Paper page
- 10.1152/jn.1998.79.2.1017 · DOI · Paper page
Cited by
Dimensionality reduction for large-scale neural recordings
Cunningham, J. P., & Yu, B. M. (2014) · Nature Neuroscience · doi:10.1038/nn.3776 · Cited by 1,219
“Dimensionality reduction has been applied to the activity of approximately 100 of the 800 neurons in the locust antennal lobe, and the population activity traces out loops that are organized by stimulus condition.”
MethodSelf-citationNeural constraints on learning
Sadtler, P. T., Quick, K. M., Golub, M. D., Chase, S. M., Ryu, S. I., Tyler-Kabara, E. C., Yu, B. M., & Batista, A. P. (2014) · Nature · doi:10.1038/nature13665 · Cited by 713
Self-citationNeural Manifolds for the Control of Movement
Gallego, J. A., Perich, M. G., Miller, L. E., & Solla, S. A. (2017) · Neuron · doi:10.1016/j.neuron.2017.05.025 · Cited by 674
Computation Through Neural Population Dynamics
Vyas, S., Golub, M. D., Sussillo, D., & Shenoy, K. V. (2020) · Annual Review of Neuroscience · doi:10.1146/annurev-neuro-092619-094115 · Cited by 671
Self-citationLong-term stability of cortical population dynamics underlying consistent behavior
Gallego, J. A., Perich, M. G., Chowdhury, R. H., Solla, S. A., & Miller, L. E. (2020) · Nature Neuroscience · doi:10.1038/s41593-019-0555-4 · Cited by 405
Metadata
- Authors
- Santhanam, G., Yu, B. M., Gilja, V., Ryu, S. I., Afshar, A., Sahani, M., & Shenoy, K. V.
- Venue
- Journal of Neurophysiology
- Publisher
- American Physiological Society
- Published
- 2009-08
- Volume
- 102
- Issue
- 2
- Pages
- 1315-1330
- ISSN
- 0022-3077 (ISSN-L)
- 1522-1598
- OpenAlex
- W2158496664
- Cited by
- 116
- References
- 16
- FWCI
- 1.83
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.