# tancik/fourier-feature-networks

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

Repository: https://github.com/tancik/fourier-feature-networks
Canonical: https://ross.abutalabs.com/products/fourier-feature-networks
Homepage: https://people.eecs.berkeley.edu/~bmild/fourfeat/
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2023-01-17T21:33:18+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2269, "days_push": 1324, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1370, forks 141 (observed 2026-08-28T04:04:31.956287+00:00)

## What it is
Research code accompanying the NeurIPS 2020 paper 'Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains'. It provides a demo notebook and experiment scripts showing how Fourier feature mappings help MLPs learn high-frequency functions.

## Use cases
- learn how Fourier feature mappings improve MLP regression
- reproduce paper experiments on high-frequency function learning
- understand spectral bias and the neural tangent kernel
- fit high-frequency signals like images and audio with an MLP
- study techniques behind NeRF-style coordinate networks

## When to choose
- you want reference implementations of Fourier feature mappings from the original paper
- you are studying spectral bias in neural networks
- you need a Colab-ready demo of coordinate-based MLPs

## When to avoid
- you need a production-ready library with maintained APIs
- you want a general-purpose deep learning framework
- you need active support or new features

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing
- domain: machine-learning, deep-learning, computer-vision, graphics
- platform: python
- tags: fourier-features, neural-tangent-kernel, mlp, research-paper, jupyter-notebook, spectral-bias, neural-representation

## Member repositories
- tancik/fourier-feature-networks (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:31.956287+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:40:56.320800+00:00, confidence not recorded.
  - readme: https://github.com/tancik/fourier-feature-networks (fetched 2026-08-28T04:04:31.956287+00:00, sha 29bf083b6456)
- Data as of 2026-08-30T08:39:29.467469+00:00.