Jove
Visualize
Contact Us
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

Related Concept Videos

Non-equilibrium in the Cell01:16

Non-equilibrium in the Cell

5.6K
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
5.6K
Creative Thinking01:25

Creative Thinking

1.4K
Creative thinking encompasses innovative and unconventional methods for addressing challenges, often leading to groundbreaking solutions. Instead of focusing solely on enhancing existing systems, such as increasing smartphone battery capacity, creative thinking might inspire advancements like energy-efficient batteries or processors that minimize power consumption. This multidimensional approach underscores the importance of exploring novel pathways to innovation.
Divergent thinking is the...
1.4K
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

387
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
387

You might also read

Related Articles

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

Sort by
Same author

Observation of disorder-free localization using a (2+1)D lattice gauge theory on a quantum processor.

Science (New York, N.Y.)·2026
Same author

Mapping Real-world Rebiopsy Events to Treatment Trajectories in EGFR/ALK/ROS1-Driven Non-small-cell Lung Cancer: Insights from the AURORA Cohort.

Clinical lung cancer·2026
Same author

Robot-assisted MIS transiliac sacroiliac joint fusion: Technical note.

Neuro-Chirurgie·2025
Same author

Functional Connectivity Is Stronger Between Unisensory and Multisensory Regions for Nonsimultaneous Judgments of Visual-Tactile Stimuli.

Psychophysiology·2025
Same author

First Constraint on Atmospheric Millicharged Particles with the LUX-ZEPLIN Experiment.

Physical review letters·2025
Same author

New Constraints on Cosmic Ray-Boosted Dark Matter from the LUX-ZEPLIN Experiment.

Physical review letters·2025

Related Experiment Video

Updated: Mar 18, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.1K

Understanding Innovation Engines: Automated Creativity and Improved Stochastic Optimization via Deep Learning.

A Nguyen1, J Yosinski2, J Clune3

  • 1University of Wyoming anguyen8@uwyo.edu.

Evolutionary Computation
|July 2, 2016
PubMed
Summary

The Innovation Engine algorithm uses deep neural networks to guide novelty search, overcoming limitations of human-defined novelty in complex optimization problems. This approach automates the creation of diverse and interesting solutions across various domains.

Keywords:
CPPNsGenetic algorithmsMAP-Elitesdeep neural networks

More Related Videos

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

2.0K

Related Experiment Videos

Last Updated: Mar 18, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.1K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

2.0K

Area of Science:

  • Artificial Intelligence
  • Optimization Algorithms
  • Machine Learning

Background:

  • Stochastic optimization algorithms often get trapped in local optima.
  • Novelty Search (NS) addresses this by rewarding novel behaviors but requires human-defined distance functions.
  • Applying NS to high-dimensional problems with complex phenotypes, like images, is challenging due to the difficulty of defining useful behavioral distance.

Purpose of the Study:

  • To introduce the Innovation Engine, a novel algorithm that enhances Novelty Search.
  • To replace human-crafted behavioral distance functions with a Deep Neural Network (DNN) for more effective novelty detection.
  • To explore the potential of DNN-driven novelty search for generating diverse and interesting solutions in complex domains.

Main Methods:

  • Developed the Innovation Engine algorithm, building upon Novelty Search principles.
  • Integrated a Deep Neural Network (DNN) to automatically learn and recognize abstract differences between phenotypes.
  • Implemented a simplified version of the Innovation Engine for initial validation in the image domain.

Main Results:

  • Demonstrated that DNNs can identify meaningful novelty at an abstract level, moving beyond low-level pixel variations.
  • Showcased the ability of the Innovation Engine to generate diverse image types (e.g., churches, mosques) rather than random noise.
  • Initial results suggest the potential for automated generation of interesting solutions in complex domains.

Conclusions:

  • The Innovation Engine offers a promising approach to overcome limitations of traditional Novelty Search in high-dimensional spaces.
  • DNNs can effectively serve as automated, abstract novelty detectors, enabling more sophisticated exploration.
  • The algorithm has the potential to automate the creation of novel solutions in diverse fields like software, robotics, and art.