Optical-mode neural network by use of the non-linear response of a laser diode to external optical feedback

E.C. Mos; J.J.H.B. Schleipen; H. Waardt, de

doi:10.1364/AO.36.006654

Optical-mode neural network by use of the non-linear response of a laser diode to external optical feedback

E.C. Mos, J.J.H.B. Schleipen, H. Waardt, de

Research output: Contribution to journal › Article › Academic › peer-review

20 Citations (Scopus)

1 Downloads (Pure)

Abstract

We present an intelligent all-optical neural network using a single laser diode that is provided with controlled external feedback. The outputs of the laser neural network (LNN) are represented in the optical domain by the longitudinal cavity modes of the laser diode. The inputs to the LNN are applied by means of adjusting the external feedback of each longitudinal mode through an optical vector-matrix multiplier. Supervised training of some basic input-output mappings is demonstrated by means of a stochastic learning algorithm. The stability and reproducibility of the LNN setup is examined.

Original language	English
Pages (from-to)	6654-6663
Number of pages	10
Journal	Applied Optics
Volume	36
Issue number	26
DOIs	https://doi.org/10.1364/AO.36.006654
Publication status	Published - 1997

Access to Document

10.1364/AO.36.006654

Cite this

@article{25cf5402e13142cdaad440a7a69bd229,

title = "Optical-mode neural network by use of the non-linear response of a laser diode to external optical feedback",

abstract = "We present an intelligent all-optical neural network using a single laser diode that is provided with controlled external feedback. The outputs of the laser neural network (LNN) are represented in the optical domain by the longitudinal cavity modes of the laser diode. The inputs to the LNN are applied by means of adjusting the external feedback of each longitudinal mode through an optical vector-matrix multiplier. Supervised training of some basic input-output mappings is demonstrated by means of a stochastic learning algorithm. The stability and reproducibility of the LNN setup is examined.",

author = "E.C. Mos and J.J.H.B. Schleipen and {Waardt, de}, H.",

year = "1997",

doi = "10.1364/AO.36.006654",

language = "English",

volume = "36",

pages = "6654--6663",

journal = "Applied Optics",

issn = "0003-6935",

publisher = "Optical Society of America (OSA)",

number = "26",

}

TY - JOUR

T1 - Optical-mode neural network by use of the non-linear response of a laser diode to external optical feedback

AU - Mos, E.C.

AU - Schleipen, J.J.H.B.

AU - Waardt, de, H.

PY - 1997

Y1 - 1997

N2 - We present an intelligent all-optical neural network using a single laser diode that is provided with controlled external feedback. The outputs of the laser neural network (LNN) are represented in the optical domain by the longitudinal cavity modes of the laser diode. The inputs to the LNN are applied by means of adjusting the external feedback of each longitudinal mode through an optical vector-matrix multiplier. Supervised training of some basic input-output mappings is demonstrated by means of a stochastic learning algorithm. The stability and reproducibility of the LNN setup is examined.

AB - We present an intelligent all-optical neural network using a single laser diode that is provided with controlled external feedback. The outputs of the laser neural network (LNN) are represented in the optical domain by the longitudinal cavity modes of the laser diode. The inputs to the LNN are applied by means of adjusting the external feedback of each longitudinal mode through an optical vector-matrix multiplier. Supervised training of some basic input-output mappings is demonstrated by means of a stochastic learning algorithm. The stability and reproducibility of the LNN setup is examined.

U2 - 10.1364/AO.36.006654

DO - 10.1364/AO.36.006654

M3 - Article

SN - 0003-6935

VL - 36

SP - 6654

EP - 6663

JO - Applied Optics

JF - Applied Optics

IS - 26

ER -

Optical-mode neural network by use of the non-linear response of a laser diode to external optical feedback

Abstract

Access to Document

Fingerprint

Cite this