AI-Feynman
AI-Feynman copied to clipboard
SJ001
The try-except was removed from the following block: try: succ_grad = evaluate_derivatives(pathdir,filename,model_feynman) except: succ_grad = 0 Execution error at grad_evaluated = evaluate_derivatives(directory, filename, model_feynman) File “.../site-packages/torch/nn/functional.py”, line 1847, in linear...
Say my input is ```x0...x8 result``` so 9 symbols and a result. I know that the resulting equation should include x0 to x8 and they are independent variables. (Meaning they...
Say I have an equation with N input symbols and the result is an integer. So in the results right now I'd have a value like 4. What I'd want...
Thank you for your work. I'm trying to run the package on some data and would love to get rid of the trigonometric functions. I created a new ops.txt file...
Hello. I am trying to execute the first example code of AI-Feynman, following its GitHub repository procedure. I have done $ pip install aifeynman, and executed the below codes at...
Hi, I've correctly installed feynman-ai and all the packages. I can run the code on the GPU, but when I execute the example.py file, I face the following error: ```...
Hello, I managed to pip install aifeynman on Windows using Miniconda and MinGW's gfortran. When testing on a simple example, I get this error message: Traceback (most recent call last):...
When I input a dataset which contains large values (10000 and larger), AI-Feynman outputs a function whose graph seems to have no relation to the input values. I then divided...
Hi, Is there a possibility to change the some of the hyperparameters, such as the tolerance for symmetry and validation error tolerance for neural network, when running run_aifeynman? Thank you...
I tried to test the Hill equation with y = (x**h)/(x**h+K**h), where h and K are parameters (both are positive rational numbers). Here are my settings: BF_try_time = 60 BF_ops_file_type="14ops"...
