Comments (1)
Hi, thank you for your kind words! maybe you can treat E as a separate trainable parameter, and use the PINN loss as your loss function. However, you can only get one eigenvalue at one time. But if you try initializing E with different values, you may get multiple solutions. Here is an example for PDE: https://kindxiaoming.github.io/pykan/Examples/Example_6_PDE.html, I guess your only modification is to add E as a trainable parameter (and register it to optimizer).
from pykan.
Related Issues (20)
- HELP!CUDA cannot be used with my own dataset HOT 4
- 维度不一致 HOT 1
- Why do you need test data in fit? HOT 2
- Manufacturing Dataset Model does not perform at all HOT 2
- Prediction Model Not Working -Using Own Inputs in a KAN y equation keeps churning out same number no matter what inputs are used HOT 1
- Linearize first layer HOT 2
- What happen when all losses turn to nan???? HOT 4
- Why the performance of KAN is different between different GPUs?
- Training for regression with unknown target labels HOT 1
- Size mismatch when using model.prune() in "hellokan" file HOT 3
- How do I compute gradient of loss function in KAN Model
- Range of initial grid HOT 3
- AttributeError: 'MultKAN' object has no attribute 'mask' HOT 1
- How to make OOT prediction ?
- Symbolic formula is incorrect when using multiplication nodes with mult_arity=4 HOT 2
- Increasing number of grid points during training HOT 1
- Optimize redundant code.
- name 'KAN' is not defined HOT 1
- Formula for Number of Trainable Parameters HOT 1
- Quick question: why should you pass in the input in order to plot the network?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pykan.