There's been a fair bit of buzz about Kolmogorov-Arnold networks online lately. Some research papers were posted around claiming that they offer better accuracy or faster training compared to traditional neural networks/MLPs for the same parameter count. I was compelled by these claims and decided to test them out myself. Here are my main findings if you're not interested in reading through the details: KANs definitely don't feel like a silver bullet, and they require significant tuning to get...