دورية أكاديمية
Hybrid Neural Autoencoders for Stimulus Encoding in Visual and Other Sensory Neuroprostheses.
| العنوان: | Hybrid Neural Autoencoders for Stimulus Encoding in Visual and Other Sensory Neuroprostheses. |
|---|---|
| المؤلفون: | Granley J; Department of Computer Science, University of California, Santa Barbara., Relic L; Department of Computer Science, University of California, Santa Barbara., Beyeler M; Department of Computer Science, University of California, Santa Barbara; Department of Psychological & Brain Sciences, University of California, Santa Barbara. |
| المصدر: | Advances in neural information processing systems [Adv Neural Inf Process Syst] 2022 Dec; Vol. 35, pp. 22671-22685. |
| نوع المنشور: | Journal Article |
| اللغة: | English |
| بيانات الدورية: | Publisher: Curran Associates Country of Publication: United States NLM ID: 9607483 Publication Model: Print Cited Medium: Internet ISSN: 1049-5258 (Print) Linking ISSN: 10495258 NLM ISO Abbreviation: Adv Neural Inf Process Syst Subsets: PubMed not MEDLINE |
| أسماء مطبوعة: | Publication: <2007>- : Red Hook, NY : Curran Associates Original Publication: San Mateo, CA : Morgan Kaufmann Publishers, c1989- |
| مستخلص: | Sensory neuroprostheses are emerging as a promising technology to restore lost sensory function or augment human capabilities. However, sensations elicited by current devices often appear artificial and distorted. Although current models can predict the neural or perceptual response to an electrical stimulus, an optimal stimulation strategy solves the inverse problem: what is the required stimulus to produce a desired response? Here, we frame this as an end-to-end optimization problem, where a deep neural network stimulus encoder is trained to invert a known and fixed forward model that approximates the underlying biological system. As a proof of concept, we demonstrate the effectiveness of this hybrid neural autoencoder (HNA) in visual neuroprostheses. We find that HNA produces high-fidelity patient-specific stimuli representing handwritten digits and segmented images of everyday objects, and significantly outperforms conventional encoding strategies across all simulated patients. Overall this is an important step towards the long-standing challenge of restoring high-quality vision to people living with incurable blindness and may prove a promising solution for a variety of neuroprosthetic technologies. |
| References: | Nature. 2016 Nov 09;539(7628):284-288. (PMID: 27830790) J Neurophysiol. 2010 Sep;104(3):1484-96. (PMID: 20610784) Prog Retin Eye Res. 2003 Sep;22(5):607-55. (PMID: 12892644) Front Neurosci. 2017 Aug 23;11:445. (PMID: 28878616) Front Neurosci. 2020 Mar 26;14:262. (PMID: 32292328) Clin Neurophysiol. 2020 Jun;131(6):1383-1398. (PMID: 31866339) Proc IEEE Int Conf Acoust Speech Signal Process. 2013 May;2013:8629-8633. (PMID: 25435816) J Acoust Soc Am. 1997 Oct;102(4):2403-11. (PMID: 9348698) Invest Ophthalmol Vis Sci. 2003 Dec;44(12):5362-9. (PMID: 14638739) J Clin Invest. 2021 Dec 1;131(23):. (PMID: 34665780) Curr Opin Neurobiol. 2019 Oct;58:21-29. (PMID: 31325670) Proc Natl Acad Sci U S A. 2013 Nov 5;110(45):18279-84. (PMID: 24127595) J Neural Eng. 2019 Apr;16(2):026008. (PMID: 30523981) Nature. 2018 Nov;563(7729):65-71. (PMID: 30382197) J Vis. 2022 Feb 1;22(2):20. (PMID: 35703408) Prog Retin Eye Res. 2016 Jan;50:89-107. (PMID: 26404104) Proc Natl Acad Sci U S A. 2017 Jul 11;114(28):E5693-E5702. (PMID: 28652360) IEEE Trans Biomed Circuits Syst. 2016 Jun;10(3):654-67. (PMID: 26390501) Bioelectron Med. 2018 Aug 13;4:12. (PMID: 32232088) Transl Vis Sci Technol. 2021 Aug 12;10(10):7. (PMID: 34383875) Vision Res. 2009 Jun;49(12):1493-506. (PMID: 19504749) Front Hum Neurosci. 2019 Jan 31;13:13. (PMID: 30766483) J Neural Eng. 2022 Jun 20;19(3):. (PMID: 35667363) Curr Opin Neurobiol. 2003 Dec;13(6):696-706. (PMID: 14662371) Ear Hear. 2008 Aug;29(4):618-26. (PMID: 18469714) Transl Vis Sci Technol. 2020 Dec 18;9(13):32. (PMID: 33384886) Vision Res. 2009 Aug;49(17):2157-63. (PMID: 19539641) Nature. 1991 Jul 18;352(6332):236-8. (PMID: 1857418) J Acoust Soc Am. 2000 Nov;108(5 Pt 1):2377-87. (PMID: 11108378) J Neurophysiol. 2006 Oct;96(4):1772-88. (PMID: 16672301) J Neural Eng. 2018 Dec;15(6):066033. (PMID: 30245482) J Neural Eng. 2017 Oct;14(5):051003. (PMID: 28612755) Ear Hear. 2005 Aug;26(4):371-80. (PMID: 16079632) ASAIO J. 2000 Jan-Feb;46(1):3-9. (PMID: 10667705) Annu Int Conf IEEE Eng Med Biol Soc. 2021 Nov;2021:4477-4481. (PMID: 34892213) PLoS One. 2021 Feb 10;16(2):e0229189. (PMID: 33566851) Am J Ophthalmol. 2016 Oct;170:100-109. (PMID: 27491695) J Mot Behav. 2012;44(6):403-18. (PMID: 23237464) Sci Transl Med. 2014 Oct 8;6(257):257ra138. (PMID: 25298320) Sci Rep. 2019 Jun 24;9(1):9199. (PMID: 31235711) |
| معلومات مُعتمدة: | R00 EY029329 United States EY NEI NIH HHS |
| تواريخ الأحداث: | Date Created: 20230918 Latest Revision: 20230920 |
| رمز التحديث: | 20231215 |
| مُعرف محوري في PubMed: | PMC10504858 |
| PMID: | 37719469 |
| قاعدة البيانات: | MEDLINE |
| تدمد: | 1049-5258 |
|---|