Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

International Conference on Electrical, Communication, and Computer Engineering (ICECCE)

Quantization of Energies with Machine Learning Without Quantum Mechanics

Huber Nieto–Chaupis

Published Oct 30, 2024• 0 citations
Publisher

Abstract

The field of Machine Learning through the technique of artificial neural network is used to determine in a straightforward manner the quantized energies of a particle in an infinite well. To accomplish this, unphysical mathematical assumptions have been applied. In essence, the opted method in this study aims to derive quantization without any knowledge of quantum mechanics of system. Moreover, the Schrödlnger equation has been reconstructed from the information of quantization derived from the usage of neural network. This procedure, although rather artificial might be exploited to derive other quantum mechanics equations without any knowledge to priori of system under study.

DOI
10.1109/icecce63537.2024.10823608

Related papers

Theory and Simulation of Perceptron Through Quantum Mechanics Formalism

Huber Nieto–Chaupis

Inside field of Machine Learning or ML one finds the formulation of artificial neural networks or ANN as a robust method to predict data under minimal bias. It constitutes a key procedure inside field of Artificial Intelligence that has demonstrated to be fast, efficient and autonomous in some cases. A deep understanding at the usage of ANN would lead to construct advanced as well as robust tools to predict behavior of systems. Mathematically speaking, once data has been trained, ML emerges as a powerful algorithm to predict unseen data but with a certain probability. Inspired in Quantum Mechanics being a theory fundamental in physic based at probabilities one can wonder if ANN based at the concept of perceptron might be improved through a mathematical methodology by using the formalism of Quantum Mechanics. The aim of paper is to explore novel mathematical mechanisms that would allow to fine the probabilities of prediction inside ML.

IEEE Biennial Congress of Argentina (ARGENCON)•Sep 18, 2024•0 citations

Perturbed Perceptron's Input to Derive Schrödinger Equation in Artificial Neural Networks

Huber Nieto–Chaupis

With the arrival of powerful computers and advanced algorithms, the searching of new fundamental equations describing our universe, is expected. In this manner, artificial intelligence might to be able to reproduce known equations in physics, for example. By using known equations, the exploration and potential discover on new mathematical structures that could be hidden, can be successfully done. Because of this, in this paper an engineered perceptron is proposed to derive in a straightforward manner the well-known Schrodinger equation. Assumptions ¨ about quantum mechanics neither related formalism were not used. Instead, perceptron is perturbed in their inputs. Once summation is applied, activation is carried out by setting the nullity of that. Therefore, a mathematical scheme to extract the physics meaning of this artificial neuron, is applied. Along the involved processes the evolution operator emerges inherently, fact that smooth the path to Schrodinger equation

International Conference on Computing, Networking, Telecommunications & Engineering Sciences Applications (CoNTESA)•Dec 18, 2024•1 citation

Calculating Energies of 1D Quantum Harmonic Oscillator with Artificial Neural Networks

Huber Nieto-Chaupis

We employ the simplest representation of perceptron and orthogonal polynomials, to derive the quantized energies of an one-dimension harmonic oscillator by using mathematical methodologies that are interpreted in terms of quantum language. In contrast to standard mechanisms based in the usage of annihilation and creation operators, the oscillator turns out to be quantized. Indeed, a generalization is presented, fact that might be interpreted as a path to quantize 2D and 3D oscillators. From the Schrödinger equation, the respective solution namely the wave function for present case is also estimated in a closed-form. In the present case, the well-known integer-order Bessel functions are employed. The resultant energy spectra are in agree with quantum mechanics calculations.

International Conference on Engineering and Emerging Technologies (ICEET)•Oct 22, 2025•0 citations

Method to Solve Quantum Few-Body Problems with Artificial Neural Networks

Hiroki Saito

A machine learning technique to obtain the ground states of quantum few-body systems using artificial neural networks is developed. Bosons in continuous space are considered and a neural network is optimized in such a way that when particle positions are input into the network, the ground-state wave function is output from the network. The method is applied to the Calogero-Sutherland model in one-dimensional space and Efimov bound states in three-dimensional space.

arXiv:1804.06521•Journal of the Physical Society of Japan•Jun 19, 2018•48 citations

A Tutorial on the Use of Physics-Informed Neural Networks to Compute the Spectrum of Quantum Systems

Lorenzo Brevi, Antonio Mandarino, Enrico Prati

Quantum many-body systems are of great interest for many research areas, including physics, biology, and chemistry. However, their simulation is extremely challenging, due to the exponential growth of the Hilbert space with system size, making it exceedingly difficult to parameterize the wave functions of large systems by using exact methods. Neural networks and machine learning, in general, are a way to face this challenge. For instance, methods like tensor networks and neural quantum states are being investigated as promising tools to obtain the wave function of a quantum mechanical system. In this tutorial, we focus on a particularly promising class of deep learning algorithms. We explain how to construct a Physics-Informed Neural Network (PINN) able to solve the Schrödinger equation for a given potential, by finding its eigenvalues and eigenfunctions. This technique is unsupervised, and utilizes a novel computational method in a manner that is barely explored. PINNs are a deep learning method that exploit automatic differentiation to solve integro-differential equations in a mesh-free way. We show how to find both the ground and the excited states. The method discovers the states progressively by starting from the ground state. We explain how to introduce inductive biases in the loss to exploit further knowledge of the physical system. Such additional constraints allow for a faster and more accurate convergence. This technique can then be enhanced by a smart choice of collocation points in order to take advantage of the mesh-free nature of the PINN. The methods are made explicit by applying them to the infinite potential well and the particle in a ring, a challenging problem to be learned by an artificial intelligence agent due to the presence of complex-valued eigenfunctions and degenerate states

arXiv:2407.20669•Technologies•Sep 26, 2024•18 citations

Neural-network-based multistate solver for a static Schrödinger equation

Hong Li, Qilong Zhai, Jeff Z. Y. Chen

Solving a multivariable static Schr\"odinger equation for a quantum system, to produce multiple excited-state energy eigenvalues and wave functions, is one of the basic tasks in mathematical and computational physics. Here we propose a neural-network-based solver, which enables us to cover the high-dimensional variable space for this purpose. The efficiency of the solver is analyzed by examples aimed at demonstrating the concept and various aspects of the task: the simultaneous finding of multiple excited states of lowest energies, the computation of energy-degenerate states with orthogonalized wave functions, the scalability to handle a multivariable problem, and the self-consistent determination and automatic adjustment of the imbedded Monte Carlo procedure. The solver adheres to the computational techniques developed in machine learning and is vastly different from traditional numerical methods.

Physical Review A•Mar 8, 2021•34 citations
The field of Machine Learning through the technique of artificial neural network is used to determine in a straightforward manner the quantized energies of a particle in an infinite well. To accomplish this, unphysical mathematical assumptions have been applied. In essence, the opted method in this study aims to derive quantization without any knowledge of quantum mechanics of system. Moreover, the Schrödlnger equation has been reconstructed from the information of quantization derived from the usage of neural network. This procedure, although rather artificial might be exploited to derive other quantum mechanics equations without any knowledge to priori of system under study.
Inside field of Machine Learning or ML one finds the formulation of artificial neural networks or ANN as a robust method to predict data under minimal bias. It constitutes a key procedure inside field of Artificial Intelligence that has demonstrated to be fast, efficient and autonomous in some cases. A deep understanding at the usage of ANN would lead to construct advanced as well as robust tools to predict behavior of systems. Mathematically speaking, once data has been trained, ML emerges as a powerful algorithm to predict unseen data but with a certain probability. Inspired in Quantum Mechanics being a theory fundamental in physic based at probabilities one can wonder if ANN based at the concept of perceptron might be improved through a mathematical methodology by using the formalism of Quantum Mechanics. The aim of paper is to explore novel mathematical mechanisms that would allow to fine the probabilities of prediction inside ML.
With the arrival of powerful computers and advanced algorithms, the searching of new fundamental equations describing our universe, is expected. In this manner, artificial intelligence might to be able to reproduce known equations in physics, for example. By using known equations, the exploration and potential discover on new mathematical structures that could be hidden, can be successfully done. Because of this, in this paper an engineered perceptron is proposed to derive in a straightforward manner the well-known Schrodinger equation. Assumptions ¨ about quantum mechanics neither related formalism were not used. Instead, perceptron is perturbed in their inputs. Once summation is applied, activation is carried out by setting the nullity of that. Therefore, a mathematical scheme to extract the physics meaning of this artificial neuron, is applied. Along the involved processes the evolution operator emerges inherently, fact that smooth the path to Schrodinger equation
We employ the simplest representation of perceptron and orthogonal polynomials, to derive the quantized energies of an one-dimension harmonic oscillator by using mathematical methodologies that are interpreted in terms of quantum language. In contrast to standard mechanisms based in the usage of annihilation and creation operators, the oscillator turns out to be quantized. Indeed, a generalization is presented, fact that might be interpreted as a path to quantize 2D and 3D oscillators. From the Schrödinger equation, the respective solution namely the wave function for present case is also estimated in a closed-form. In the present case, the well-known integer-order Bessel functions are employed. The resultant energy spectra are in agree with quantum mechanics calculations.
Quantum many-body systems are of great interest for many research areas, including physics, biology, and chemistry. However, their simulation is extremely challenging, due to the exponential growth of the Hilbert space with system size, making it exceedingly difficult to parameterize the wave functions of large systems by using exact methods. Neural networks and machine learning, in general, are a way to face this challenge. For instance, methods like tensor networks and neural quantum states are being investigated as promising tools to obtain the wave function of a quantum mechanical system. In this tutorial, we focus on a particularly promising class of deep learning algorithms. We explain how to construct a Physics-Informed Neural Network (PINN) able to solve the Schrödinger equation for a given potential, by finding its eigenvalues and eigenfunctions. This technique is unsupervised, and utilizes a novel computational method in a manner that is barely explored. PINNs are a deep learning method that exploit automatic differentiation to solve integro-differential equations in a mesh-free way. We show how to find both the ground and the excited states. The method discovers the states progressively by starting from the ground state. We explain how to introduce inductive biases in the loss to exploit further knowledge of the physical system. Such additional constraints allow for a faster and more accurate convergence. This technique can then be enhanced by a smart choice of collocation points in order to take advantage of the mesh-free nature of the PINN. The methods are made explicit by applying them to the infinite potential well and the particle in a ring, a challenging problem to be learned by an artificial intelligence agent due to the presence of complex-valued eigenfunctions and degenerate states
Solving a multivariable static Schr\"odinger equation for a quantum system, to produce multiple excited-state energy eigenvalues and wave functions, is one of the basic tasks in mathematical and computational physics. Here we propose a neural-network-based solver, which enables us to cover the high-dimensional variable space for this purpose. The efficiency of the solver is analyzed by examples aimed at demonstrating the concept and various aspects of the task: the simultaneous finding of multiple excited states of lowest energies, the computation of energy-degenerate states with orthogonalized wave functions, the scalability to handle a multivariable problem, and the self-consistent determination and automatic adjustment of the imbedded Monte Carlo procedure. The solver adheres to the computational techniques developed in machine learning and is vastly different from traditional numerical methods.