Saved in:
Bibliographic Details
Main Authors: Bersier, Stephane, Chen-Lin, Xinyi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.11776
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914973811212288
author Bersier, Stephane
Chen-Lin, Xinyi
author_facet Bersier, Stephane
Chen-Lin, Xinyi
contents Despite the wide variety of input types in machine learning, this diversity is often not fully reflected in their representations or model architectures, leading to inefficiencies throughout a model's lifecycle. This paper introduces an algebraic approach to constructing input-encoding architectures that properly account for the data's structure, providing a step toward achieving more typeful machine learning.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11776
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Encoding architecture algebra
Bersier, Stephane
Chen-Lin, Xinyi
Machine Learning
Artificial Intelligence
Programming Languages
Software Engineering
Despite the wide variety of input types in machine learning, this diversity is often not fully reflected in their representations or model architectures, leading to inefficiencies throughout a model's lifecycle. This paper introduces an algebraic approach to constructing input-encoding architectures that properly account for the data's structure, providing a step toward achieving more typeful machine learning.
title Encoding architecture algebra
topic Machine Learning
Artificial Intelligence
Programming Languages
Software Engineering
url https://arxiv.org/abs/2410.11776