Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains · HackerPapers discussions

Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains — mentioned by mnky9800n

Sun, 12 Jan 2025 09:44:09 GMT

For example https://arxiv.org/abs/2006.10739

Paper and discussion history. A mention is not an endorsement.

Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains — mentioned by allangrant

Mon, 21 Aug 2023 04:30:05 GMT

A video about neural networks, function approximation, machine learning, and mathematical building blocks. This is a submission for #SoME3 (0:00) Functions Describe the World (3:15) Neural Architecture (5:35) Higher Dimensions (11:55) Taylor Series (15:20) Fourier Series (21:25) The Real World (24:32) An Open Challenge Links and Content: • On Mathematical Maturity, Thomas Garrity: https://youtube.com/watch?v=zHU1xH6Ogs4 • Earth Rotation Loop: https://youtube.com/watch?v=aiQdLP2mBJE • Earth Rotation Loop Modeling Shell Surfaces: https://www.geogebra.org/m/xtv7zpn5 • Fourier Features Paper…

Paper and discussion history. A mention is not an endorsement.

Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains — mentioned by gessha

Tue, 28 Feb 2023 15:48:50 GMT

In a recent-ish paper, there was an analysis of positional encodings using Neural Tangent Kernels which showed positional encodings are very similar to Fourier transformations of the inputs: Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains, https://arxiv.org/abs/2006.10739

Paper and discussion history. A mention is not an endorsement.