A feedforward neural network approach to solving systems of linear equations

Rashad Al-Jawfi

doi:10.5269/bspm.78591

Rashad Al-Jawfi prof

Résumé

This paper proposes a neural network-based framework for solving systems of linear equations of the form $\mathbf{A}\mathbf{x} = \mathbf{b}$. The method reformulates the problem as a residual minimization task and employs a feedforward neural network to learn the mapping from input matrix-vector pairs to solution vectors. The network is trained using synthetic data and optimized via gradient descent using residual-based loss. Experimental results demonstrate that the model achieves high accuracy for well-conditioned systems with dimensions up to $n = 20$, producing residual errors below $10^{-4}$ in most cases. Comparative analysis against classical numerical solvers shows that while traditional methods remain superior for ill-conditioned systems, the neural approach offers notable advantages in inference speed, generalization, and suitability for parallel or real-time deployment. Limitations and future enhancements—including scalability, noise robustness, and hybridization—are also discussed.

Téléchargements

Les données sur le téléchargement ne sont pas encore disponible.

Références

Strang, G. (2006). Linear Algebra and Its Applications (4th ed.). Thomson, Brooks/Cole.

Saad, Y. (2003). Iterative Methods for Sparse Linear Systems (2nd ed.). SIAM.

Benzi, M. (2002). Preconditioning techniques for large linear systems: A survey. Journal of Computational Physics, 182(2), 418–477.

Haykin, S. (2009). Neural Networks and Learning Machines (3rd ed.). Pearson Education.

LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444.

Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533–536.

Gao, X., & Wang, J. (2003). A recurrent neural network for solving linear equations. Neural Processing Letters, 17(1), 59–71.

Zhang, X., & Wang, J. (2004). Global exponential convergence of neural networks for solving linear equations. IEEE Transactions on Circuits and Systems I: Regular Papers, 51(9), 1783–1790.

Hussain, A., Zhu, Q., & Nandi, A. K. (2020). A survey on neural network-based numerical solvers for systems of equations. Neural Computing and Applications, 32(8), 4423–4444.

Trefethen, L. N., & Bau, D. (1997). Numerical Linear Algebra. SIAM.

Higham, N. J. (2002). Accuracy and Stability of Numerical Algorithms (2nd ed.). SIAM.

Nair, V., & Hinton, G. E. (2010). Rectified linear units improve restricted Boltzmann machines. In Proceedings of the 27th International Conference on Machine Learning (ICML-10), 807–814.

Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.

Abadi, M., et al. (2016). TensorFlow: A system for large-scale machine learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI), 265–283.

Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.