A Modified Batch Intrinsic Plasticity Method for Pre-training the Random Coefficients of Extreme Learning Machines

Abstract

In extreme learning machines (ELM) the hidden-layer coefficients are randomly set and fixed, while the output-layer coefficients of the neural network are computed by a least squares method. The randomly-assigned coefficients in ELM are known to influence its performance and accuracy significantly. In this paper we present a modified batch intrinsic plasticity (modBIP) method for pre-training the random coefficients in the ELM neural networks. The current method is devised based on the same principle as the batch intrinsic plasticity (BIP) method, namely, by enhancing the information transmission in every node of the neural network. It differs from BIP in two prominent aspects. First, modBIP does not involve the activation function in its algorithm, and it can be applied with any activation function in the neural network. In contrast, BIP employs the inverse of the activation function in its construction, and requires the activation function to be invertible (or monotonic). The modBIP method can work with the often-used non-monotonic activation functions (e.g. Gaussian, swish, Gaussian error linear unit, and radial-basis type functions), with which BIP breaks down. Second, modBIP generates target samples on random intervals with a minimum size, which leads to highly accurate computation results when combined with ELM. The combined ELM/modBIP method is markedly more accurate than ELM/BIP in numerical simulations. Ample numerical experiments are presented with shallow and deep neural networks for function approximation and boundary/initial value problems with partial differential equations. They demonstrate that the combined ELM/modBIP method produces highly accurate simulation results, and that its accuracy is insensitive to the random-coefficient initializations in the neural network. This is in sharp contrast with the ELM results without pre-training of the random coefficients.

arXiv comment33 pages, 26 figures

References in corpus (18)

• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• Gaussian Error Linear Units (GELUs)
• Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
• DGM: A deep learning algorithm for solving partial differential equations
• An Energy Approach to the Solution of Partial Differential Equations in Computational Mechanics via Machine Learning: Concepts, Implementation and Applications
• Stochastic Configuration Networks: Fundamentals and Algorithms
• Weak Adversarial Networks for High-dimensional Partial Differential Equations
• Local Extreme Learning Machines and Domain Decomposition for Solving Linear and Nonlinear Partial Differential Equations
• A Method for Representing Periodic Functions and Enforcing Exactly Periodic Boundary Conditions with Deep Neural Networks
• MgNet: A Unified Framework of Multigrid and Convolutional Neural Network
• The Finite Neuron Method and Convergence Analysis
• Fast, simple and accurate handwritten digit classification by training shallow neural network classifiers with the 'extreme learning machine' algorithm
• Multiphase Flows of N Immiscible Incompressible Fluids: A Reduction-Consistent and Thermodynamically-Consistent Formulation and Associated Algorithm
• Efficient Deep Learning Techniques for Multiphase Flow Simulation in Heterogeneous Porous Media
• Wall-bounded multiphase flows of N immiscible incompressible fluids: consistency and contact-angle boundary condition
• A Convective-like Energy-Stable Open Boundary Condition for Simulations of Incompressible Flows
• A pressure correction scheme for generalized form of energy-stable open boundary conditions for incompressible flows
• Deep Coregionalization for the Emulation of Spatial-Temporal Fields

Cited by in corpus (9)

• Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations
• On Computing the Hyperparameter of Extreme Learning Machines: Algorithm and Application to Computational PDEs, and Comparison with Classical and High-Order Finite Elements
• Parsimonious Physics-Informed Random Projection Neural Networks for Initial-Value Problems of ODEs and index-1 DAEs
• Numerical Approximation of Partial Differential Equations by a Variable Projection Method with Artificial Neural Networks
• A Method for Computing Inverse Parametric PDE Problems with Random-Weight Neural Networks
• Numerical Solution and Bifurcation Analysis of Nonlinear Partial Differential Equations with Extreme Learning Machines
• Fredholm Neural Networks
• Eig-PIELM: A Mesh-Free Approach for Efficient Eigen-Analysis with Physics-Informed Extreme Learning Machines
• Numerical Solution of Stiff ODEs with Physics-Informed RPNNs