KAN: Kolmogorov–Arnold Networks
Put the learnable functions on the edges, not the nodes — splines replace fixed activations.
Liu et al. · arXiv 2024 · Foundations. Read the paper ↗
A free, interactive, animated visual explainer of KAN: Kolmogorov–Arnold Networks — every exhibit computed from the real formulas, with verbatim quotes from the source.
Questions
- What is KAN: Kolmogorov–Arnold Networks?
- Put the learnable functions on the edges, not the nodes — splines replace fixed activations.
- Who published KAN: Kolmogorov–Arnold Networks, and where?
- Liu et al. — arXiv 2024 (arXiv:2404.19756).
- Where can I find a visual explainer of KAN: Kolmogorov–Arnold Networks?
- Right here — a free, interactive, animated walkthrough of the whole paper, with exhibits computed from the real formulas and verbatim quotes from the source.
Related explainers
- Attention Is All You Need
- GPT-3: Language Models are Few-Shot Learners
- Mixtral of Experts
- Training Compute-Optimal Large Language Models
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- BERT: Pre-training of Deep Bidirectional Transformers
- Scaling Laws for Neural Language Models
- Adam: A Method for Stochastic Optimization