Implicit Neural Representations with Periodic Activation Functions · HackerPapers discussions

Implicit Neural Representations with Periodic Activation Functions — HN submission

Fri, 25 Sep 2026 07:30:00 GMT

Implicit Neural Representations with Periodic Activation Functions (2020)

3 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Implicit Neural Representations with Periodic Activation Functions — mentioned by stefanpie

Mon, 04 Sep 2023 20:47:39 GMT

Another approach to neural-based data representation / encoding / decoding is Implicit Neural Representations (INRs). For INRs, you overfit a neural network, typically a Multilayer Perceptron (MLP)[1], to a single data point. For instance, in the case of a single image (the data point), the inputs would be the xy pixel coordinates—usually scaled from [0, n_pixels]^2 to either [0, 1]^2 or [-1, 1]^2—and the outputs would be the RGB values of each pixel. Once trained on pixels from this singular image, the INR model essentially becomes a representation of that data point. The image can then be…

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

Implicit Neural Representations with Periodic Activation Functions — mentioned by f_devd

Wed, 01 Mar 2023 08:04:12 GMT

Could also be Sirens[1] which was all about sin as activation, while sinusoidal positional encoding are (iirc) just from the original transformer paper. [1]: https://arxiv.org/abs/2006.09661

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

Implicit Neural Representations with Periodic Activation Functions — mentioned by _0ffh

Fri, 19 Jun 2020 08:44:32 GMT

Paper on arxiv at https://arxiv.org/abs/2006.09661

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