Towards a Quantum Field Theory for Optical Artificial Intelligence

Today, several socio-techno-economic drivers are steering the evolution of Telecommunications and Internet towards a growing exploitation of ultra-broadband infrastructures (e.g., 5G) and Artificial Intelligence (AI) systems. Focusing on the most promising AI technological approaches, Deep Neural Networks (DNNs) are outperforming in several applications domains. One of the possible explanations, elaborated in literature, is that DNN functioning is deeply rooted in the principles of theoretical Physics, specifically Quantum Field Theory (QFT) and Gauge theory. This is encouraging even more researches and experiments in the direction of a full exploitation of quantum computing and networking for the development of innovative Information Communication Technologies (ICT) and AI systems. In this innovation avenue, given that QFT and Gauge theory have been already proposed for modeling the brain and biological nervous systems, this paper explores the intriguing possibility of exploiting QFT principles also for future DNN, for instance by using electromagnetic waves effects in metamaterials. This appears to be a promising direction of future studies and experiments: therefore, the paper also describes the architecture of a simple optical DNN prototype, based on metamaterials, which is intended as a live test-bed, for simulations and experiments.

[1]  W. Freeman,et al.  Dissipation and spontaneous symmetry breaking in brain dynamics , 2007, q-bio/0701053.

[2]  Andrea Alù,et al.  Performing Mathematical Operations with Metamaterials , 2014, Science.

[3]  Jae-weon Lee.  Quantum Fields as Deep Learning , 2017, Journal of the Korean Physical Society.

[4]  Max Welling,et al.  Spherical CNNs , 2018, ICLR.

[5]  Geoffrey E. Hinton,et al.  Keeping the neural networks simple by minimizing the description length of the weights , 1993, COLT '93.

[6]  Yi Luo,et al.  All-optical machine learning using diffractive deep neural networks , 2018, Science.

[7]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[8]  David R. Smith,et al.  Controlling Electromagnetic Fields , 2006, Science.

[9]  Karl J. Friston,et al.  Knowing one's place: a free-energy approach to pattern regulation , 2015, Journal of The Royal Society Interface.

[10]  Antonio Manzalini,et al.  Horizon 2020 and Beyond: On the 5G Operating System for a True Digital Society , 2015, IEEE Vehicular Technology Magazine.

[11]  David J. Schwab,et al.  An exact mapping between the Variational Renormalization Group and Deep Learning , 2014, ArXiv.

[12]  K. Wilson,et al.  The Renormalization group and the epsilon expansion , 1973 .

[13]  Karl J. Friston.  The free-energy principle: a unified brain theory? , 2010, Nature Reviews Neuroscience.

[14]  Karl J. Friston.  Hierarchical Models in the Brain , 2008, PLoS Comput. Biol..

[15]  Max Welling,et al.  Gauge Equivariant Convolutional Networks and the Icosahedral CNN 1 , 2019 .

[16]  P. Howe,et al.  Multicritical points in two dimensions, the renormalization group and the ϵ expansion , 1989 .

[17]  G. Vitiello.  My double unveiled , 2001 .

[18]  Claudio Conti,et al.  Observation of replica symmetry breaking in disordered nonlinear wave propagation , 2017, Nature Communications.

[19]  L. O'raifeartaigh,et al.  Gauge theory: Historical origins and some modern developments , 2000 .

[20]  O. Seeberg.  Statistical Mechanics. — A Set of Lectures , 1975 .

[21]  Karl J. Friston,et al.  Towards a Neuronal Gauge Theory , 2016, PLoS biology.