Statistical mechanics of lossy data compression using a nonmonotonic perceptron

Tadaaki Hosaka¹, Yoshiyuki Kabashima, Hidetoshi Nishimori

¹Department of Computational Intelligence and Systems Science, Tokyo Institute of Technology, Yokohama 2268502, Japan. hosaka@sp.sis.titech.ac.jp

Physical Review. E, Statistical, Nonlinear, and Soft Matter Physics

|January 7, 2003

Abstract:

The performance of a lossy data compression scheme for uniformly biased Boolean messages is investigated via methods of statistical mechanics. Inspired by a formal similarity to the storage capacity problem in neural network research, we utilize a perceptron of which the transfer function is appropriately designed in order to compress and decode the messages. Employing the replica method, we analytically show that our scheme can achieve the optimal performance known in the framework of lossy compression in most cases when the code length becomes infinite. The validity of the obtained results is numerically confirmed.

Related Experiment Videos

Statistical mechanics of lossy data compression using a nonmonotonic perceptron

Related Concept Videos

Exact mapping of a spin glass with correlated disorder to the pure Ising model.

Learning Transitions in Classical Ising Models and Deformed Toric Codes.

Quantum effects in rotationally invariant spin glass models.

Temperature chaos as a logical consequence of the reentrant transition in spin glasses.

Graph neural networks for integrated information and major complex estimation.

Evaluation of information flows in the RAS-MAPK system using transfer entropy measurements.

Tension on dsDNA bound to ssDNA-RecA filaments may play an important role in driving efficient and accurate homology recognition and strand exchange.

Publisher's Note: Amplitude-phase coupling drives chimera states in globally coupled laser networks [Phys. Rev. E 91, 040901(R) (2015)].

Erratum: Shapes of sedimenting soft elastic capsules in a viscous fluid [Phys. Rev. E 92, 033003 (2015)].

Erratum: Attenuation of excitation decay rate due to collective effect [Phys. Rev. E 90, 022142 (2014)].

Publisher's Note: Role of connectivity and fluctuations in the nucleation of calcium waves in cardiac cells [Phys. Rev. E 92, 052715 (2015)].

Publisher's Note: Lattice Boltzmann approach for complex nonequilibrium flows [Phys. Rev. E 92, 043308 (2015)].

A long short-term memory network with SHAP interpretability for dynamic prediction of ICU delirium: development and external validation.

Association of total Q/R ratio with myocardial scar in patients with chronic total occlusion.

Physical layer security for CO-OFDM based on chaotic real-imaginary component shuffling and dynamic Latin square permutation.

Inter-hospital ICU-to-ICU transfer of critically ill COVID-19 patients is not associated with increased mortality: a systematic review with exploratory meta-analysis.

[Analysis of Risk Factors and Construction of Predictive Model for Iliac Vein Compression Syndrome Combined with Deep Vein Thrombosis of the Lower Extremities].

Longitudinal Study of Anxiety and Depression During COVID-19 Lockdown: A Secondary Data Analysis.

Related Experiment Videos

Statistical mechanics of lossy data compression using a nonmonotonic perceptron

Abstract:

Related Concept Videos

Related Articles