Online learning in neural decoding using incremental linear discriminant analysis

Yaesop Lee; Sreenuj Chellath Madayambath; Yanzhou Liu; Da Ting Lin; Rong Chen; Shuvra S. Bhattacharyya

doi:10.1109/CBS.2017.8266092

Online learning in neural decoding using incremental linear discriminant analysis

Yaesop Lee^*
, Sreenuj Chellath Madayambath
, Yanzhou Liu
, Da Ting Lin
, Rong Chen
, Shuvra S. Bhattacharyya

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

8 Citations (Scopus)

Abstract

Neural decoding focuses on predicting behavior variables based on neural activities. Linear discriminant analysis (LDA) has been successfully used in pattern recognition and machine learning to find the set of discriminant vectors to characterize two or more classes of objects. However, LDA cannot be directly used for real-time neural decoding problems. In this paper, we propose an incremental LDA with online learning method to overcome this limitation. The dataflow techniques are implemented in the LIDE (LIghtweight Dataflow Environment), which provides capabilities to systematically optimize and integrate embedded software components for signal and information processing. Using these techniques along with online learning, an efficient real-time neural decoding system can be attained.

Original language	English
Title of host publication	2017 IEEE International Conference on Cyborg and Bionic Systems, CBS 2017
Publisher	IEEE
Pages	173-177
Number of pages	5
ISBN (Electronic)	9781538631942
DOIs	https://doi.org/10.1109/CBS.2017.8266092
Publication status	Published - 19 Jan 2018
Publication type	A4 Article in conference proceedings
Event	IEEE International Conference on Cyborg and Bionic Systems - Beijing, China Duration: 17 Oct 2017 → 19 Oct 2017

Conference

Conference	IEEE International Conference on Cyborg and Bionic Systems
Country/Territory	China
City	Beijing
Period	17/10/17 → 19/10/17

Keywords

dataflow
ILDA
incremental learning
Neural decoding
online learning

Publication forum classification

Publication forum level 1

ASJC Scopus subject areas

Control and Optimization
Artificial Intelligence

Access to Document

10.1109/CBS.2017.8266092

Cite this

@inproceedings{a80d3bfaef6c4081a5cd220e23ba8cab,

title = "Online learning in neural decoding using incremental linear discriminant analysis",

abstract = "Neural decoding focuses on predicting behavior variables based on neural activities. Linear discriminant analysis (LDA) has been successfully used in pattern recognition and machine learning to find the set of discriminant vectors to characterize two or more classes of objects. However, LDA cannot be directly used for real-time neural decoding problems. In this paper, we propose an incremental LDA with online learning method to overcome this limitation. The dataflow techniques are implemented in the LIDE (LIghtweight Dataflow Environment), which provides capabilities to systematically optimize and integrate embedded software components for signal and information processing. Using these techniques along with online learning, an efficient real-time neural decoding system can be attained.",

keywords = "dataflow, ILDA, incremental learning, Neural decoding, online learning",

author = "Yaesop Lee and Madayambath, \{Sreenuj Chellath\} and Yanzhou Liu and Lin, \{Da Ting\} and Rong Chen and Bhattacharyya, \{Shuvra S.\}",

year = "2018",

month = jan,

day = "19",

doi = "10.1109/CBS.2017.8266092",

language = "English",

pages = "173--177",

booktitle = "2017 IEEE International Conference on Cyborg and Bionic Systems, CBS 2017",

publisher = "IEEE",

address = "United States",

note = "IEEE International Conference on Cyborg and Bionic Systems ; Conference date: 17-10-2017 Through 19-10-2017",

}

Lee, Y, Madayambath, SC, Liu, Y, Lin, DT, Chen, R & Bhattacharyya, SS 2018, Online learning in neural decoding using incremental linear discriminant analysis. in 2017 IEEE International Conference on Cyborg and Bionic Systems, CBS 2017. IEEE, pp. 173-177, IEEE International Conference on Cyborg and Bionic Systems, Beijing, China, 17/10/17. https://doi.org/10.1109/CBS.2017.8266092

TY - GEN

T1 - Online learning in neural decoding using incremental linear discriminant analysis

AU - Lee, Yaesop

AU - Madayambath, Sreenuj Chellath

AU - Liu, Yanzhou

AU - Lin, Da Ting

AU - Chen, Rong

AU - Bhattacharyya, Shuvra S.

PY - 2018/1/19

Y1 - 2018/1/19

N2 - Neural decoding focuses on predicting behavior variables based on neural activities. Linear discriminant analysis (LDA) has been successfully used in pattern recognition and machine learning to find the set of discriminant vectors to characterize two or more classes of objects. However, LDA cannot be directly used for real-time neural decoding problems. In this paper, we propose an incremental LDA with online learning method to overcome this limitation. The dataflow techniques are implemented in the LIDE (LIghtweight Dataflow Environment), which provides capabilities to systematically optimize and integrate embedded software components for signal and information processing. Using these techniques along with online learning, an efficient real-time neural decoding system can be attained.

AB - Neural decoding focuses on predicting behavior variables based on neural activities. Linear discriminant analysis (LDA) has been successfully used in pattern recognition and machine learning to find the set of discriminant vectors to characterize two or more classes of objects. However, LDA cannot be directly used for real-time neural decoding problems. In this paper, we propose an incremental LDA with online learning method to overcome this limitation. The dataflow techniques are implemented in the LIDE (LIghtweight Dataflow Environment), which provides capabilities to systematically optimize and integrate embedded software components for signal and information processing. Using these techniques along with online learning, an efficient real-time neural decoding system can be attained.

KW - dataflow

KW - ILDA

KW - incremental learning

KW - Neural decoding

KW - online learning

U2 - 10.1109/CBS.2017.8266092

DO - 10.1109/CBS.2017.8266092

M3 - Conference contribution

SP - 173

EP - 177

BT - 2017 IEEE International Conference on Cyborg and Bionic Systems, CBS 2017

PB - IEEE

T2 - IEEE International Conference on Cyborg and Bionic Systems

Y2 - 17 October 2017 through 19 October 2017

ER -

Online learning in neural decoding using incremental linear discriminant analysis

Abstract

Conference

Keywords

Publication forum classification

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this