User contributions for 2601:644:600:46D0:6220:8AFC:7EC5:14A9

27 February 2025

• 09:3909:39, 27 February 2025 diff hist +39,330 N Universal approximation theorem →Arbitrary depth: See the bottom of the GeLU paper (https://arxiv.org/pdf/1606.08415). Swish is a specific case of the GeLU and was discovered afterwards. Swish is now no longer used current