Physics-informed neural networks with caputo-fabrizio derivatives for nonlinear fractal-fractional delay equations and chaotic systems
Hafsa Khan, Muhammad Sulaiman, Ghaylen Laouini, Izaz Ur Rahman, Mohammed Abdullah Salman · 2026
Read Physics-informed neural networks with caputo-fabrizio derivatives for nonlinear fractal-fractional delay equations and chaotic systems by Hafsa Khan, Muhammad Sulaiman, Ghaylen Laouini, Izaz Ur Rahman, Mohammed Abdullah Salman (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13473503.txt.
Description
Hafsa Khan and colleagues put forward a neural network method in 2026 for equations with memory and delay effects. Such equations model odd spread patterns, memory circuits, and swirling fluid motion. The new method, called PINN-CF, trains a network to honor the physics rules inside the equation itself. It uses a smooth memory kernel that avoids sharp faults found in older forms.
Four test problems checked the method, from delayed growth rules to circuit models. Error levels stayed very low across the tests, near the floor set for the runs. Charts of error over training backed up the headline scores. The work gives modelers a flexible solver for systems where the past shapes the present.
Catalog record
| CREATOR | Hafsa Khan, Muhammad Sulaiman, Ghaylen Laouini, Izaz Ur Rahman, Mohammed Abdullah Salman |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 164414 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |