Ziming Liu @ZimingLiu11 · 01 May 2024
MLPs are so foundational, but are there alternatives? MLPs place activation functions on neurons, but can we instead place (learnable) activation functions on weights? Yes, we KAN! We propose Kolmogorov-Arnold Networks (KAN), which are more accurate and interpretable than MLPs.🧵 https://t.co/4Soe2M7NfG
1 027 987Views
5 011Likes
1 027Reposts
113Replies
253Quotes
3 513Bookmarks
Is that a lot?
181×vs this author's median5 665 views is typical
100Percentile for this authorof 4 recent posts
374×vs 10K–100K median2 747 views is typical
71.1× audienceReachviews ÷ followers
0.62%Engagement rateof viewers reacted