Machine Learning for Neural Decoding

Abstract

Despite rapid advances in machine learning tools, the majority of neural decoding approaches still use traditional methods. Modern machine learning tools, which are versatile and easy to use, have the potential to significantly improve decoding performance. This tutorial describes how to effectively apply these algorithms for typical decoding problems. We provide descriptions, best practices, and code for applying common machine learning methods, including neural networks and gradient boosting. We also provide detailed comparisons of the performance of various methods at the task of decoding spiking activity in motor cortex, somatosensory cortex, and hippocampus. Modern methods, particularly neural networks and ensembles, significantly outperform traditional approaches, such as Wiener and Kalman filters. Improving the performance of neural decoding algorithms allows neuroscientists to better understand the information contained in a neural population and can help to advance engineering applications such as brain–machine interfaces. Our code package is available at github.com/kordinglab/neural_decoding .

Shown for reading. Its publisher allows quoting it, not republishing it.

References 75

1. 1.

   Arora S, Cohen N, Hu W, Luo Y (2019 ) Implicit regularization in deep matrix factorization. Adv Neural Inf Process Syst, pp 7411–7422.

   Not in our library

2. 2.

   Baeg E, Kim Y, Huh K, Mook-Jung I, Kim H, Jung M (2003 ) Dynamics of population code for working memory in the prefrontal cortex. Neuron 40:177–188.

   Not in our library10.1016/s0896-6273(03)00597-x

3. 3.

   Barbieri R, Wilson MA, Frank LM, Brown EN (2005 ) An analysis of hippocampal spatio-temporal representations using a Bayesian algorithm for neural spike train decoding. IEEE Trans Neural Syst Rehabil Eng 13:131–136.

   Not in our library10.1109/tnsre.2005.847368

4. 4.
   Modern Machine Learning as a Benchmark for Fitting Neural Responses · 2018

   Not checked
5. 5.

   Bergstra J, Bengio Y (2012 ) Random search for hyper-parameter optimization. J Mach Learn Res 13:281–305.

   Not in our library

6. 6.

   Bergstra J, Yamins D, Cox DD (2013 ) Making a science of model search: hyperparameter optimization in hundreds of dimensions for vision architectures. Proc Mach Learn Res 28:115–123.

   Not in our library

7. 7.

   Bishop CM (2006 ) Pattern recognition and machine learning. New York: Springer.

   Not in our library

8. 8.

   Breiman L (2017 ) Classification and regression trees. Boca Raton, FL: CRC.

   Not in our library

9. 9.
   Learning to Control a Brain–Machine Interface for Reaching and Grasping by Primates · 2003

   No notice
10. 10.

    Chang C-C, Lin C-J (2011 ) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2:1–27.

    Not in our library10.1145/1961189.1961199

11. 11.

    Chen T (2014 ) Introduction to boosted trees. University of Washington Computer Science 22:115.

    Not in our library

12. 12.

    Chen T, Guestrin C (2016 ) XGBoost: a scalable tree boosting system In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 785–794. New York: ACM.

    Not in our library

13. 13.

    Cho K, Van Merriënboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014 ) Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv:1406.1078.

    Not in our library

14. 14.

    Collinger JL, Wodlinger B, Downey JE, Wang W, Tyler-Kabara EC, Weber DJ, McMorland AJ, Velliste M, Boninger ML, Schwartz AB (2013 ) High-performance neuroprosthetic control by an individual with tetraplegia. Lancet 381:557–564.

    Not in our library10.1016/s0140-6736(12)61816-9

15. 15.

    Corbett E, Perreault E, Koerding K (2010 ) Mixture of time-warped trajectory models for movement decoding. Adv Neural Inf Process Syst, pp 433–441.

    Not in our library

16. 16.

    Cranmer M, Sanchez-Gonzalez A, Battaglia P, Xu R, Cranmer K, Spergel D, Ho S (2020 ) Discovering symbolic models from deep learning with inductive biases. arXiv:2006.11287.

    Not in our library

17. 17.

    Dankers C, Kronseder V, Wagner M, Casalicchio G (2020 ) Introduction to feature importance In: Limitations of ML Interpretability. Munich, Germany: Department of Statistics, LMU Munich.

    Not in our library

18. 18.

    Davidson TJ, Kloosterman F, Wilson MA (2009 ) Hippocampal replay of extended experience. Neuron 63:497–507.

    Not in our library10.1016/j.neuron.2009.07.027

19. 19.

    Dekleva BM, Ramkumar P, Wanda PA, Kording KP, Miller LE (2016 ) Uncertainty leads to persistent effects on reach representations in dorsal premotor cortex. Elife 5:e14316

    Not in our library10.7554/elife.14316

20. 20.

    Ethier C, Oby ER, Bauman MJ, Miller LE (2012 ) Restoration of grasp following paralysis through brain-controlled stimulation of muscles. Nature 485:368–371.

    Not in our library10.1038/nature10987

21. 21.

    Fagg AH, Ojakangas GW, Miller LE, Hatsopoulos NG (2009 ) Kinetic trajectory decoding using motor cortical ensembles. IEEE Trans Neural Syst Rehabil Eng 17:487–496.

    Not in our library10.1109/tnsre.2009.2029313

22. 22.

    Farshchian A, Gallego JA, Cohen JP, Bengio Y, Miller LE, Solla SA (2018 ) Adversarial domain adaptation for stable brain-machine interfaces. arXiv:1810.00045.

    Not in our library

23. 23.

    Friedman J, Hastie T, Tibshirani R (2001 ) The elements of statistical learning. New York: Springer.

    Not in our library

24. 24.

    Gao P, Trautmann E, Byron MY, Santhanam G, Ryu S, Shenoy K, Ganguli S (2017 ) A theory of multineuronal dimensionality, dynamics and measurement. bioRxiv. Advance online publication. Retrieved Nov 12, 2017. doi:10.1101/214262.

    Not in our library

25. 25.

    Gilja V, Nuyujukian P, Chestek CA, Cunningham JP, Yu BM, Fan JM, Churchland MM, Kaufman MT, Kao JC, Ryu SI, Shenoy KV (2012 ) A high-performance neural prosthesis enabled by control algorithm design. Nat Neurosci 15:1752–1757.

    Not in our library10.1038/nn.3265

26. 26.
    Population coding of conditional probability distributions in dorsal premotor cortex · 2018

    Not checked
27. 27.

    Glaser JI, Benjamin AS, Farhoodi R, Kording KP (2019 ) The roles of supervised machine learning in systems neuroscience. Prog Neurobiol 175:126–137.

    Not in our library10.1016/j.pneurobio.2019.01.008

28. 28.

    Goodfellow I, Bengio Y, Courville A (2016 ) Deep learning. Cambridge, MA: MIT.

    Not in our library

29. 29.

    Hastie T, Tibshirani R, Friedman J (2009 ) The elements of statistical learning: data mining, inference, and prediction. New York: Springer Science and Business Media.

    Not in our library

30. 30.

    He K, Zhang X, Ren S, Sun J (2015 ) Delving deep into rectifiers: surpassing human-level performance on ImageNet classification In: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), pp 1026–1034.

    Not in our library10.1109/iccv.2015.123

31. 31.

    Hernández A, Nácher V, Luna R, Zainos A, Lemus L, Alvarez M, Vázquez Y, Camarillo L, Romo R (2010 ) Decoding a perceptual decision process across cortex. Neuron 66:300–314.

    Not in our library10.1016/j.neuron.2010.03.031

32. 32.

    Hochreiter S, Schmidhuber J (1997 ) Long short-term memory. Neural Comput 9:1735–1780.

    Not in our library10.1162/neco.1997.9.8.1735

33. 33.

    Hoerl AE, Kennard RW (1970 ) Ridge regression: biased estimation for nonorthogonal problems. Technometrics 12:55–67.

    Not in our library10.1080/00401706.1970.10488634

34. 34.

    Hung CP, Kreiman G, Poggio T, DiCarlo JJ (2005 ) Fast readout of object identity from macaque inferior temporal cortex. Science 310:863–866.

    Not in our library10.1126/science.1117593

35. 35.

    Ibos G, Freedman DJ (2017 ) Sequential sensory and decision processing in posterior parietal cortex. Elife 6:e23743

    Not in our library10.7554/elife.23743

36. 36.

    Kaggle (2020 ) Kaggle. Available at https://www.kaggle.com.

    Not in our library

37. 37.

    Kao JC, Stavisky SD, Sussillo D, Nuyujukian P, Shenoy KV (2014 ) Information systems opportunities in brain–machine interface decoders. Proc IEEE 102:666–682.

    Not in our library10.1109/jproc.2014.2307357

38. 38.

    Kao JC, Nuyujukian P, Ryu SI, Shenoy KV (2017 ) A high-performance neural prosthesis incorporating discrete state selection with hidden Markov models. IEEE Trans Biomed Eng 64:935–945.

    Not in our library10.1109/tbme.2016.2582691

39. 39.

    Kloosterman F, Layton SP, Chen Z, Wilson MA (2014 ) Bayesian decoding using unsorted spikes in the rat hippocampus. J Neurophysiol 111:217–227.

    Not in our library10.1152/jn.01046.2012

40. 40.

    Kriegeskorte N, Douglas PK (2019 ) Interpreting encoding and decoding models. Curr Opin Neurobiol 55:167–179.

    Not in our library10.1016/j.conb.2019.04.002

Cited by papers we hold 2

• Preserved neural dynamics across animals performing similar behaviour · 2023
  No notice
• A Comparison of Neural Decoding Methods and Population Coding Across Thalamo-Cortical Head Direction Cells · 2019
  Not checked

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.