Saved in:
Bibliographic Details
Main Authors: Bleiberg, Yair, Werman, Michael
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.05052
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910689272004608
author Bleiberg, Yair
Werman, Michael
author_facet Bleiberg, Yair
Werman, Michael
contents Coordinate-based Multi-Layer Perceptrons (MLPs) are known to have difficulty reconstructing high frequencies of the training data. A common solution to this problem is Positional Encoding (PE), which has become quite popular. However, PE has drawbacks. It has high-frequency artifacts and adds another hyper-hyperparameter, just like batch normalization and dropout do. We believe that under certain circumstances PE is not necessary, and a smarter construction of the network architecture together with a smart training method is sufficient to achieve similar results. In this paper, we show that very simple MLPs can quite easily output a frequency when given input of the half-frequency and quarter-frequency. Using this, we design a network architecture in blocks, where the input to each block is the output of the two previous blocks along with the original input. We call this a {\it Fibonacci Network}. By training each block on the corresponding frequencies of the signal, we show that Fibonacci Networks can reconstruct arbitrarily high frequencies.
format Preprint
id arxiv_https___arxiv_org_abs_2411_05052
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The Fibonacci Network: A Simple Alternative for Positional Encoding
Bleiberg, Yair
Werman, Michael
Machine Learning
Coordinate-based Multi-Layer Perceptrons (MLPs) are known to have difficulty reconstructing high frequencies of the training data. A common solution to this problem is Positional Encoding (PE), which has become quite popular. However, PE has drawbacks. It has high-frequency artifacts and adds another hyper-hyperparameter, just like batch normalization and dropout do. We believe that under certain circumstances PE is not necessary, and a smarter construction of the network architecture together with a smart training method is sufficient to achieve similar results. In this paper, we show that very simple MLPs can quite easily output a frequency when given input of the half-frequency and quarter-frequency. Using this, we design a network architecture in blocks, where the input to each block is the output of the two previous blocks along with the original input. We call this a {\it Fibonacci Network}. By training each block on the corresponding frequencies of the signal, we show that Fibonacci Networks can reconstruct arbitrarily high frequencies.
title The Fibonacci Network: A Simple Alternative for Positional Encoding
topic Machine Learning
url https://arxiv.org/abs/2411.05052