Saved in:
Bibliographic Details
Main Author: Guo, Cheng
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2210.13004
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929311451185152
author Guo, Cheng
author_facet Guo, Cheng
contents Utilizing an abstract information processing model based on minimal yet realistic assumptions inspired by biological systems, we study how to achieve the early visual system's two ultimate objectives: efficient information transmission and accurate sensor probability distribution modeling. We prove that optimizing for information transmission does not guarantee optimal probability distribution modeling in general. We illustrate, using a two-pixel (2D) system and image patches, that an efficient representation can be realized through a nonlinear population code driven by two types of biologically plausible loss functions that depend solely on output. After unsupervised learning, our abstract information processing model bears remarkable resemblances to biological systems, despite not mimicking many features of real neurons, such as spiking activity. A preliminary comparison with a contemporary deep learning model suggests that our model offers a significant efficiency advantage. Our model provides novel insights into the computational theory of early visual systems as well as a potential new approach to enhance the efficiency of deep learning models.
format Preprint
id arxiv_https___arxiv_org_abs_2210_13004
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Efficient Representation of Natural Image Patches
Guo, Cheng
Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
Neurons and Cognition
Utilizing an abstract information processing model based on minimal yet realistic assumptions inspired by biological systems, we study how to achieve the early visual system's two ultimate objectives: efficient information transmission and accurate sensor probability distribution modeling. We prove that optimizing for information transmission does not guarantee optimal probability distribution modeling in general. We illustrate, using a two-pixel (2D) system and image patches, that an efficient representation can be realized through a nonlinear population code driven by two types of biologically plausible loss functions that depend solely on output. After unsupervised learning, our abstract information processing model bears remarkable resemblances to biological systems, despite not mimicking many features of real neurons, such as spiking activity. A preliminary comparison with a contemporary deep learning model suggests that our model offers a significant efficiency advantage. Our model provides novel insights into the computational theory of early visual systems as well as a potential new approach to enhance the efficiency of deep learning models.
title Efficient Representation of Natural Image Patches
topic Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
Neurons and Cognition
url https://arxiv.org/abs/2210.13004