Jove
Visualize
Contact Us

Related Experiment Videos

A prospective and retrospective look at the diffusion model.

Everett M Rogers1

  • 1Department of Communication and Journalism, University of New Mexico, Albuquerque, New Mexico 87131-1171, USA. erogers@unm.edu

Journal of Health Communication
|February 13, 2004
PubMed
Summary

This article explores the origins and evolution of diffusion models over 30 years. It also discusses future prospects for this important machine learning technique.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A framework for research utilization applied to seven case studies.

American journal of preventive medicine·2007
Same author

Diffusion of clean indoor air ordinances in the southwestern United States.

Health education & behavior : the official publication of the Society for Public Health Education·2007
Same author

Small-area variations in conviction rates for DWI: the significance of contextual variables in a Southwestern state.

Accident; analysis and prevention·2006
Same author

Exploring health promotion agenda-setting in New Mexico: reshaping health promotion leadership.

Promotion & education·2004
Same author

Effectiveness of customized Victim Impact Panels on first-time DWI offender inmates.

Accident; analysis and prevention·2003
Same author

Diffusion of preventive innovations.

Addictive behaviors·2002
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Computer Vision

Background:

  • Diffusion models are a class of generative models.
  • These models have gained significant attention in recent years.
  • Understanding their development is crucial for advancing AI.

Purpose of the Study:

  • To provide a historical overview of diffusion models.
  • To highlight key evolutionary advancements in diffusion model architectures and applications.
  • To forecast future research directions and potential impacts of diffusion models.

Main Methods:

  • Literature review of seminal and recent publications on diffusion models.
  • Analysis of key architectural innovations and algorithmic improvements.
  • Synthesis of trends and expert opinions on future prospects.

Main Results:

  • The diffusion model was initially conceptualized decades ago.
  • Significant advancements have occurred in areas like sampling speed and conditional generation.
  • Current research focuses on improving efficiency and expanding applications.

Conclusions:

  • Diffusion models have a rich history and have undergone substantial evolution.
  • Their future prospects are bright, with potential for transformative applications in various AI domains.
  • Continued research is essential to overcome current limitations and unlock full potential.

Related Experiment Videos