Randomly Weighted Neuromodulation in Neural Networks Facilitates Learning of Manifolds Common Across Tasks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hong, Jinyung, Pavlic, Theodore P.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916081306697728
author Hong, Jinyung
Pavlic, Theodore P.
author_facet Hong, Jinyung
Pavlic, Theodore P.
contents Geometric Sensitive Hashing functions, a family of Local Sensitive Hashing functions, are neural network models that learn class-specific manifold geometry in supervised learning. However, given a set of supervised learning tasks, understanding the manifold geometries that can represent each task and the kinds of relationships between the tasks based on them has received little attention. We explore a formalization of this question by considering a generative process where each task is associated with a high-dimensional manifold, which can be done in brain-like models with neuromodulatory systems. Following this formulation, we define \emph{Task-specific Geometric Sensitive Hashing~(T-GSH)} and show that a randomly weighted neural network with a neuromodulation system can realize this function.
format Preprint
id arxiv_https___arxiv_org_abs_2401_02437
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Randomly Weighted Neuromodulation in Neural Networks Facilitates Learning of Manifolds Common Across Tasks
Hong, Jinyung
Pavlic, Theodore P.
Neural and Evolutionary Computing
Computer Vision and Pattern Recognition
Machine Learning
Geometric Sensitive Hashing functions, a family of Local Sensitive Hashing functions, are neural network models that learn class-specific manifold geometry in supervised learning. However, given a set of supervised learning tasks, understanding the manifold geometries that can represent each task and the kinds of relationships between the tasks based on them has received little attention. We explore a formalization of this question by considering a generative process where each task is associated with a high-dimensional manifold, which can be done in brain-like models with neuromodulatory systems. Following this formulation, we define \emph{Task-specific Geometric Sensitive Hashing~(T-GSH)} and show that a randomly weighted neural network with a neuromodulation system can realize this function.
title Randomly Weighted Neuromodulation in Neural Networks Facilitates Learning of Manifolds Common Across Tasks
topic Neural and Evolutionary Computing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2401.02437