pykan

pykan copied to clipboard

rgambord

The argument for the init method is lr=1 which is okay for LBFGS. However, Adam won't function well with such high lr. lr=1 is the default learning rate in LBFGS...

kamil2oster

This pull request addresses the issue with: 1. KAN, MultKAN and utils set the random seed to be 0, unless argument as int is provided by the user. 2. The...

kamil2oster

Added step_size argument in the create_dataset utility. This is for uniform sampling of data at regular intervals.

Arjeus

Correct a comment.

adsmendesdaniel

yzy1997

yzy1997

HELP!CUDA cannot be used with my own dataset

4

**My dataset was built based on a.csv file of my own. In the previous version, I could use model.train to train the model and could use cuda normally. But now...

AnBydAm

Activation function get_layer and model.forward() results are not same

2

I want to fully understand what activation plot tell us Here is my code: ```python import numpy as np import sympy as sp import pandas as pd import matplotlib.pyplot as...

seyidcemkarakas

Hi, I was wondering if there is a built-in way to compute the gradient of loss function like in other NN using `backward()`. As well as if we can use...

Chao-Chen-2004