Approximate Probabilistic Neural Networks with Gated Threshold Logic

O. Krestinskaya; A. P. James

doi:10.1109/NANO.2018.8626302

Approximate Probabilistic Neural Networks with Gated Threshold Logic

O. Krestinskaya, A. P. James

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Scopus citations

Abstract

Probabilistic Neural Network (PNN) is a feedforward artificial neural network developed for solving classification problems. This paper proposes a hardware implementation of an approximated PNN (APNN) algorithm in which the conventional exponential function of the PNN is replaced with gated threshold logic. The weights of the PNN are approximated using a memristive crossbar architecture. In particular, the proposed algorithm performs normalization of the training weights, and quantization into 16 levels which significantly reduces the complexity of the circuit.

Original language	English (US)
Title of host publication	Proceedings of the IEEE Conference on Nanotechnology
Publisher	IEEE Computer Societyhelp@computer.org
ISBN (Print)	9781538653364
DOIs	https://doi.org/10.1109/NANO.2018.8626302
State	Published - Jan 24 2019
Externally published	Yes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2023-09-23

Access to Document

10.1109/NANO.2018.8626302

Cite this

@inproceedings{d652f0a12a8e46aa82d0f472998d535b,

title = "Approximate Probabilistic Neural Networks with Gated Threshold Logic",

abstract = "Probabilistic Neural Network (PNN) is a feedforward artificial neural network developed for solving classification problems. This paper proposes a hardware implementation of an approximated PNN (APNN) algorithm in which the conventional exponential function of the PNN is replaced with gated threshold logic. The weights of the PNN are approximated using a memristive crossbar architecture. In particular, the proposed algorithm performs normalization of the training weights, and quantization into 16 levels which significantly reduces the complexity of the circuit.",

author = "O. Krestinskaya and James, {A. P.}",

note = "Generated from Scopus record by KAUST IRTS on 2023-09-23",

year = "2019",

month = jan,

day = "24",

doi = "10.1109/NANO.2018.8626302",

language = "English (US)",

isbn = "9781538653364",

booktitle = "Proceedings of the IEEE Conference on Nanotechnology",

publisher = "IEEE Computer Societyhelp@computer.org",

}

TY - GEN

T1 - Approximate Probabilistic Neural Networks with Gated Threshold Logic

AU - Krestinskaya, O.

AU - James, A. P.

N1 - Generated from Scopus record by KAUST IRTS on 2023-09-23

PY - 2019/1/24

Y1 - 2019/1/24

N2 - Probabilistic Neural Network (PNN) is a feedforward artificial neural network developed for solving classification problems. This paper proposes a hardware implementation of an approximated PNN (APNN) algorithm in which the conventional exponential function of the PNN is replaced with gated threshold logic. The weights of the PNN are approximated using a memristive crossbar architecture. In particular, the proposed algorithm performs normalization of the training weights, and quantization into 16 levels which significantly reduces the complexity of the circuit.

AB - Probabilistic Neural Network (PNN) is a feedforward artificial neural network developed for solving classification problems. This paper proposes a hardware implementation of an approximated PNN (APNN) algorithm in which the conventional exponential function of the PNN is replaced with gated threshold logic. The weights of the PNN are approximated using a memristive crossbar architecture. In particular, the proposed algorithm performs normalization of the training weights, and quantization into 16 levels which significantly reduces the complexity of the circuit.

UR - https://ieeexplore.ieee.org/document/8626302/

UR - http://www.scopus.com/inward/record.url?scp=85062263966&partnerID=8YFLogxK

U2 - 10.1109/NANO.2018.8626302

DO - 10.1109/NANO.2018.8626302

M3 - Conference contribution

SN - 9781538653364

BT - Proceedings of the IEEE Conference on Nanotechnology

PB - IEEE Computer Societyhelp@computer.org

ER -

Approximate Probabilistic Neural Networks with Gated Threshold Logic

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this