x.com

x.com

Simulating Token Economies: Motivations and Insights - 6MV

To derive deep insights in tokenomics, 6th Man Ventures is building Agent Based Simulations for infrastructure economies.

OUR PAST, PRESENT, AND FUTURE IS ONCHAIN

Airstack Moxie Pass Shared Frame

Farcaster Frame for Moxie Shared Intro

Moxie Pass Shared Frame

Farcaster Frame for Moxie Shared Intro

User Stats

Get Your User Stats

Moxie Pass Shared Frame

Farcaster Frame for Moxie Shared Intro

Moxie Pass Intro Frame

Farcaster Frame for Moxie Pass Intro

Warpcast Followers Chart

Get Your Warpcast Stats

KAN: Kolmogorov-Arnold Networks

Inspired by the Kolmogorov-Arnold representation theorem, we propose Kolmogorov-Arnold Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs). While MLPs have fixed activation functions on nodes ("neurons"), KANs have learnable activation functions on edges ("weights"). KANs have no linear weights at all -- every weight parameter is replaced by a univariate function parametrized as a spline. We show that this seemingly simple change makes KANs outperform MLPs in terms of accuracy and interpretability. For accuracy, much smaller KANs can achieve comparable or better accuracy than much larger MLPs in data fitting and PDE solving. Theoretically and empirically, KANs possess faster neural scaling laws than MLPs. For interpretability, KANs can be intuitively visualized and can easily interact with human users. Through two examples in mathematics and physics, KANs are shown to be useful collaborators helping scientists (re)discover mathematical and physical laws. In summary, KANs are promising alternatives for MLPs, opening opportunities for further improving today's deep learning models which rely heavily on MLPs.