Ising machines, which are hardware implementations of the Ising model of coupled spins, have been influential in the development of unsupervised learning algorithms at the origins of Artificial Intelligence (AI). However, their application to AI has been limited due to the complexities in matching supervised training methods with Ising machine physics, even though these methods are essential for achieving high accuracy. In this study, we demonstrate an efficient approach to train Ising machines in a supervised way through the Equilibrium Propagation algorithm, achieving comparable results to software-based implementations. We employ the quantum annealing procedure of the D-Wave Ising machine to train a fully-connected neural network on the MNIST dataset. Furthermore, we demonstrate that the machine's connectivity supports convolution operations, enabling the training of a compact convolutional network with minimal spins per neuron. Our findings establish Ising machines as a promising trainable hardware platform for AI, with the potential to enhance machine learning applications.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11063034 | PMC |
| http://dx.doi.org/10.1038/s41467-024-46879-4 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Unsupervised Machine Learning Method for the Phase Behavior of the Constant Magnetization Ising Model in Two and Three Dimensions.
J Phys Chem B
December 2024
Department of Chemistry, University of Wisconsin-Madison, Madison, Wisconsin 53706, United States.
Machine learning methods have been important in the study of phase transitions. Unsupervised methods are particularly attractive because they do not require prior knowledge of the existence of a phase transition. In this work we focus on the constant magnetization Ising model in two (2D) and three (3D) dimensions.
View Article and Find Full Text PDFPhysically interpretable performance metrics for clustering.
J Chem Phys
December 2024
Institute for Physical Science and Technology, Biophysics Program, University of Maryland, College Park, Maryland 20742, USA.
Clustering is a type of machine learning technique, which is used to group huge amounts of data based on their similarity into separate groups or clusters. Clustering is a very important task that is nowadays used to analyze the huge and diverse amount of data coming out of molecular dynamics (MD) simulations. Typically, the data from the MD simulations in terms of their various frames in the trajectory are clustered into different groups and a representative element from each group is studied separately.
View Article and Find Full Text PDFDeterministic Versus Nondeterministic Optimization Algorithms for the Restricted Boltzmann Machine.
J Comput Cogn Eng
November 2024
Department of Computer Science, Utah Valley University, USA.
A restricted Boltzmann machine is a fully connected shallow neural network. It can be used to solve many challenging optimization problems. The Boltzmann machines are usually considered probability models.
View Article and Find Full Text PDFReconfigurable application-specific photonic integrated circuit for solving partial differential equations.
Nanophotonics
May 2024
Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL 32611, USA.
Article Synopsis
- Scientists and engineers have long sought faster and more efficient ways to solve mathematical equations, moving beyond traditional brute-force computing methods that are becoming less effective over time.
- New techniques that take advantage of natural systems' energy minimization, like annealers and Ising Machines, are gaining popularity, with a focus on programmable analog solvers that utilize Maxwell's equations and photonic circuits.
- A novel photonic integrated circuit was developed, demonstrating 90% accuracy compared to commercial solvers, and successfully tested for modeling thermal diffusion on a spacecraft’s heat shield, signaling potential applications in various scientific and engineering areas.
Composite bayesian optimization in function spaces ising NEON-Neural Epistemic Operator Networks.
Sci Rep
November 2024
Mechanical Engineering & Applied Mechanics, University of Pennsylvania, Philadelphia, PA, USA.
Operator learning is a rising field of scientific computing where inputs or outputs of a machine learning model are functions defined in infinite-dimensional spaces. In this paper, we introduce Neon (Neural Epistemic Operator Networks), an architecture for generating predictions with uncertainty using a single operator network backbone, which presents orders of magnitude less trainable parameters than deep ensembles of comparable performance. We showcase the utility of this method for sequential decision-making by examining the problem of composite Bayesian Optimization (BO), where we aim to optimize a function , where is an unknown map which outputs elements of a function space, and is a known and cheap-to-compute functional.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!