Hierarchal decomposition of neural data using Boosted Mixtures of Hidden Markov Chains and its application to a BMI

Shalom Darmanjian, Antonio Paiva, Jose Principe, Justin C. Sanchez

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose a simple algorithm that takes multidimensional neural input data and decomposes the joint likelihood into marginals using Boosted Mixtures of Hidden Markov Chains (BM-HMM). The algorithm applies techniques from boosting to create hierarchal dependencies between these marginal subspaces. Finally, borrowing ideas from mixture of experts, the local information is weighted and incorporated into an ensemble decision. Our results show that this algorithm is very simple to train and computationally efficient, while also providing the ability to reduce the input dimensionality for Brain Machine Interfaces (BMIs).

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
Pages3062-3067
Number of pages6
DOIs
StatePublished - Dec 1 2007
Externally publishedYes
Event2007 International Joint Conference on Neural Networks, IJCNN 2007 - Orlando, FL, United States
Duration: Aug 12 2007Aug 17 2007

Other

Other2007 International Joint Conference on Neural Networks, IJCNN 2007
CountryUnited States
CityOrlando, FL
Period8/12/078/17/07

Fingerprint

Markov processes
Brain
Decomposition

ASJC Scopus subject areas

  • Software

Cite this

Darmanjian, S., Paiva, A., Principe, J., & Sanchez, J. C. (2007). Hierarchal decomposition of neural data using Boosted Mixtures of Hidden Markov Chains and its application to a BMI. In IEEE International Conference on Neural Networks - Conference Proceedings (pp. 3062-3067). [4371449] https://doi.org/10.1109/IJCNN.2007.4371449

Hierarchal decomposition of neural data using Boosted Mixtures of Hidden Markov Chains and its application to a BMI. / Darmanjian, Shalom; Paiva, Antonio; Principe, Jose; Sanchez, Justin C.

IEEE International Conference on Neural Networks - Conference Proceedings. 2007. p. 3062-3067 4371449.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Darmanjian, S, Paiva, A, Principe, J & Sanchez, JC 2007, Hierarchal decomposition of neural data using Boosted Mixtures of Hidden Markov Chains and its application to a BMI. in IEEE International Conference on Neural Networks - Conference Proceedings., 4371449, pp. 3062-3067, 2007 International Joint Conference on Neural Networks, IJCNN 2007, Orlando, FL, United States, 8/12/07. https://doi.org/10.1109/IJCNN.2007.4371449
Darmanjian S, Paiva A, Principe J, Sanchez JC. Hierarchal decomposition of neural data using Boosted Mixtures of Hidden Markov Chains and its application to a BMI. In IEEE International Conference on Neural Networks - Conference Proceedings. 2007. p. 3062-3067. 4371449 https://doi.org/10.1109/IJCNN.2007.4371449
Darmanjian, Shalom ; Paiva, Antonio ; Principe, Jose ; Sanchez, Justin C. / Hierarchal decomposition of neural data using Boosted Mixtures of Hidden Markov Chains and its application to a BMI. IEEE International Conference on Neural Networks - Conference Proceedings. 2007. pp. 3062-3067
@inproceedings{abd2dd5238cd46b9a3433100caf66b90,
title = "Hierarchal decomposition of neural data using Boosted Mixtures of Hidden Markov Chains and its application to a BMI",
abstract = "In this paper, we propose a simple algorithm that takes multidimensional neural input data and decomposes the joint likelihood into marginals using Boosted Mixtures of Hidden Markov Chains (BM-HMM). The algorithm applies techniques from boosting to create hierarchal dependencies between these marginal subspaces. Finally, borrowing ideas from mixture of experts, the local information is weighted and incorporated into an ensemble decision. Our results show that this algorithm is very simple to train and computationally efficient, while also providing the ability to reduce the input dimensionality for Brain Machine Interfaces (BMIs).",
author = "Shalom Darmanjian and Antonio Paiva and Jose Principe and Sanchez, {Justin C.}",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/IJCNN.2007.4371449",
language = "English",
isbn = "142441380X",
pages = "3062--3067",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",

}

TY - GEN

T1 - Hierarchal decomposition of neural data using Boosted Mixtures of Hidden Markov Chains and its application to a BMI

AU - Darmanjian, Shalom

AU - Paiva, Antonio

AU - Principe, Jose

AU - Sanchez, Justin C.

PY - 2007/12/1

Y1 - 2007/12/1

N2 - In this paper, we propose a simple algorithm that takes multidimensional neural input data and decomposes the joint likelihood into marginals using Boosted Mixtures of Hidden Markov Chains (BM-HMM). The algorithm applies techniques from boosting to create hierarchal dependencies between these marginal subspaces. Finally, borrowing ideas from mixture of experts, the local information is weighted and incorporated into an ensemble decision. Our results show that this algorithm is very simple to train and computationally efficient, while also providing the ability to reduce the input dimensionality for Brain Machine Interfaces (BMIs).

AB - In this paper, we propose a simple algorithm that takes multidimensional neural input data and decomposes the joint likelihood into marginals using Boosted Mixtures of Hidden Markov Chains (BM-HMM). The algorithm applies techniques from boosting to create hierarchal dependencies between these marginal subspaces. Finally, borrowing ideas from mixture of experts, the local information is weighted and incorporated into an ensemble decision. Our results show that this algorithm is very simple to train and computationally efficient, while also providing the ability to reduce the input dimensionality for Brain Machine Interfaces (BMIs).

UR - http://www.scopus.com/inward/record.url?scp=51749092420&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51749092420&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2007.4371449

DO - 10.1109/IJCNN.2007.4371449

M3 - Conference contribution

SN - 142441380X

SN - 9781424413805

SP - 3062

EP - 3067

BT - IEEE International Conference on Neural Networks - Conference Proceedings

ER -