The Gâteaux-Hopfield Neural Network method
This work addresses a specific computational bottleneck in neural network-based integral equation solving, offering a significant speed improvement for researchers in applied mathematics and computational physics.
The authors tackled the problem of solving a first-order Fredholm integral equation by proposing a new differential equation set for the Hopfield Neural Network using the Linear Extended Gâteaux Derivative, resulting in a method that converges 22 times faster for α > 1 compared to the integer-order approach.
In the present work a new set of differential equations for the Hopfield Neural Network (HNN) method were established by means of the Linear Extended Gateaux Derivative (LEGD). This new approach will be referred to as Gâteaux-Hopfiel Neural Network (GHNN). A first order Fredholm integral problem was used to test this new method and it was found to converge 22 times faster to the exact solutions for α > 1 if compared with the HNN integer order differential equations. Also a limit to the learning time is observed by analysing the results for different values of α. The robustness and advantages of this new method will be pointed out.