SynodicMonth/ChebyKAN
Kolmogorov-Arnold Networks (KAN) using Chebyshev polynomials instead of B-splines.
Jupyter Notebook
Issues
- 3
ChebyKANs do not support continual learning
#8 opened by iiisak - 3
No Dropout found in any experiment
#10 opened by FabioDataGeek - 6
Poor generalization
#9 opened by buptlittlecabbage - 7
- 5
Check out KAL-Nets
#5 opened by 1ssb - 3
- 8
Tanh and infinite support
#2 opened by edmondja - 2
Use properly tuned baselines!
#1 opened by usamec