Temperature stabilization with Hebbian learning using an autonomous optoelectronic dendritic unit

Abstract

The integration of machine learning with photonic and optoelectronic components is progressing rapidly, offering the potential for high-speed bio-inspired computing platforms. In this work, we employ an experimental fiber-based dendritic structure with adaptive plasticity for a learning-and-control virtual task. Specifically, we develop a closed-loop controller embedded in a single-mode fiber optical dendritic unit (ODU) that incorporates Hebbian learning principles, and we test it in a hypothetical temperature stabilization task. Our optoelectronic system operates at 1 GHz signaling and sampling rates and applies plasticity rules through the direct modulation of semiconductor optical amplifiers. Although the input correlation (ICO) learning rule we consider here is computed digitally from the experimental output of the optoelectronic system, this output is fed back into the plastic properties of the ODU physical substrate, enabling autonomous learning. In this specific configuration, we utilize only three plastic dendritic optical branches with exclusively positive weighting. We demonstrate that, despite variations in the physical system’s parameters, the application of the ICO learning rule effectively mitigates temperature disturbances, ensuring robust performance. These results encourage an all-hardware solution, where optimizing feedback loop speed and embedding the ICO rule will enable continuous stabilization, finalizing a real-time platform operating at up to 1 GHz.

Graphical abstract

Keywords

Optoelectronic system / Fiberoptic system / Input correlation learning / Neuro-inspired computing / Optical dendritic unit

References

[1] Ang,K.H., Chong,G., Li,Y.: PID control system analysis, design, and technology. IEEE Trans. Control Syst. Technol. 13 (4), 559- 576 (2005)

[2] Radke,F., Isermann,R.: A parameter-adaptive PID-controller with stepwise parameter optimization. Automatica 23 (4), 449- 457 (1987)

[3] Soyguder,S., Karakose,M., Alli,H.: Design and simulation of self-tuning PID-type fuzzy adaptive control for an expert HVAC system. Expert Syst. Appl. 36 (3), 4566- 4573 (2009)

[4] Shuprajhaa,T., Sujit,S.K., Srinivasan,K.: Reinforcement learning based adaptive PID controller design for control of linear/nonlinear unstable processes. Appl. Soft Comput. J. 128, 109450 (2022)

[5] Kumar,R., Srivastava,S., Gupta,J.: Artificial neural network based PID controller for online control of dynamical systems. In: 2016 IEEE 1st International Conference on Power Electronics, Intelligent Control and Energy Systems (ICPEICES), pp. 1- 6 (2016)

[6] Kocur,M., Kozak,S., Dvorscak,B.: Design and implementation of FPGA-digital based PID controller. In: Proceedings of the 2014 15th International Carpathian Control Conference (ICCC), pp. 233- 236 (2014)

[7] Sung,G.M., Chiang,P.Y., Tsai,Y.Y.: Predictive direct torque control ASIC with fuzzy voltage vector control and neural network PID speed controller. In: 2021 IEEE International Future Energy Electronics Conference (IFEEC), pp. 1- 5 (2021)

[8] Gupta,M.C., Ballato,J.: The Handbook of Photonics. CRC Press, Boca Raton (2018)

[9] Dutta,N.K., Zhang,X.: Optoelectronic Devices. World Scientific, Singapore (2018)

[10] Udd,E., Benterou,J.: Improvements to high-speed monitoring of events in extreme environments using fiber bragg grating sensors. In: Fiber Optic Sensors and Applications IX, vol. 8370, pp. 155- 167 (2012)

[11] Del Villar,I., Matias,I.R.: Optical Fibre Sensors: Fundamentals for Development of Optimized Devices. Wiley-IEEE Press, Piscataway (2020)

[12] Toole,R., Tait,A.N., De Lima,T.F., Nahmias,M.A., Shastri,B.J., Prucnal,P.R., Fok,M.P.: Photonic implementation of spiketiming-dependent plasticity and learning algorithms of biological neural systems. J. Lightwave Technol. 34 (2), 470- 476 (2015)

[13] Feldmann,J., Youngblood,N., Wright,C.D., Bhaskaran,H., Pernice,W.H.: All-optical spiking neurosynaptic networks with selflearning capabilities. Nature 569 (7755), 208- 214 (2019)

[14] Huang,C., Sorger,V.J., Miscuglio,M., Al-Qadasi,M., Mukherjee,A., Lampe,L., Nichols,M., Tait,A.N., Lima,T., Marquez,B.A., et al.: Prospects and applications of photonic neural networks. Adv. Phys.: X. 7 (1), 1981155 (2022)

[15] Zheng,D., Xiang,S., Guo,X., Zhang,Y., Zeng,X., Zhu,X., Shi,Y., Chen,X., Hao,Y.: Full-function Pavlov associative learning photonic neural networks based on SOA and DFB-SA. APL Photonics 9 (2), (2024)

[16] Porr,B., Wörgötter,F.: Isotropic sequence order learning. Neural Comput. 15 (4), 831- 864 (2003)

[17] Porr,B., Wörgötter,F.: Strongly improved stability and faster convergence of temporal sequence learning by using input correlations only. Neural Comput. 18 (6), 1380- 1412 (2006)

[18] Ortín,S., Soriano,M.C., Tetzlaff,C., Wörgötter,F., Fischer,I., Mirasso,C.R., Argyris,A.: Implementation of input correlation learning with an optoelectronic dendritic unit. Front. Phys. 11, 1112295 (2023)

[19] Kulvicius,T., Kolodziejski,C., Tamosiunaite,M., Porr,B., Wörgötter,F.: Behavioral analysis of differential Hebbian learning in closed-loop systems. Biol. Cybern. 103, 255- 271 (2010)

[20] Homchanthanakul,J., Manoonpong,P.: Continuous online adaptation of bioinspired adaptive neuroendocrine control for autonomous walking robots. IEEE Trans. Neural Netw. Learn. Syst. 33 (5), 1833- 1845 (2022)

[21] Möller,K., Kappel,D., Tamosiunaite,M., Tetzlaff,C., Porr,B., Wörgötter,F.: Differential Hebbian learning with time-continuous signals for active noise reduction. PLoS ONE 17 (5), 0266679 (2022)

[22] Velanas,P., Bogris,A., Argyris,A., Syvridis,D.: High-speed all-optical first- and second-order differentiators based on crossphase modulation in fibers. J. Lightwave Technol. 26 (18), 3269- 3276 (2008)

RIGHTS & PERMISSIONS

The Author(s)