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

Heuristics01:21

Heuristics

833
Heuristics are problem-solving strategies that use mental shortcuts to simplify decision-making. Unlike algorithms, which must be followed precisely to achieve a correct result, heuristics offer a general problem-solving framework. They save time and energy but can sometimes lead to less rational decisions.
People often rely on heuristics when faced with an overload of information, limited time, low importance of the decision, limited information, or when a heuristic readily comes to mind. For...
833
Variability: Analysis01:11

Variability: Analysis

616
Measures of variability are statistical metrics that reveal the dispersion pattern within a dataset. They are pivotal in biostatistics, providing insights into the heterogeneity within health and biological data. Variability signifies the degree to which data points diverge from one another, helping researchers understand the potential range of values and associated uncertainty within the data.
The range is a simple measure of variability, indicating the difference between the highest and...
616
Methods of Medium Optimization01:28

Methods of Medium Optimization

1
Optimizing growth media enhances microbial proliferation and maximizes product yield. Statistical experimental design methodologies provide structured and reproducible approaches, offering progressively higher levels of robustness and efficiency.The One-Factor-at-a-Time (OFAT) MethodThe One-Factor-at-a-Time (OFAT) method involves adjusting a single variable while keeping all others constant. However, it cannot detect interactions between variables, often leading to suboptimal outcomes when...
1
Principle of Moments: Problem Solving01:30

Principle of Moments: Problem Solving

1.3K
The principle of moments is a fundamental concept in physics and engineering. It refers to the balancing of forces and moments around a point or axis, also known as the pivot. This principle is used in many real-life scenarios, including construction, sports, and daily activities like opening doors and pushing objects.
One such scenario involves a pole placed in a three-dimensional system with a cable attached. When a tension is applied to the cable, the moment about the z-axis passing through...
1.3K
Gene Evolution - Fast or Slow?02:05

Gene Evolution - Fast or Slow?

8.3K
The genomes of eukaryotes are punctuated by long stretches of sequence which do not code for proteins or RNAs. Although some of these regions do contain crucial regulatory sequences, the vast majority of this DNA serves no known function. Typically, these regions of the genome are the ones in which the fastest change, in evolutionary terms, is observed, because there is typically little to no selection pressure acting on these regions to preserve their sequences.
In contrast, regions which code...
8.3K
Gene Evolution - Fast or Slow?02:05

Gene Evolution - Fast or Slow?

3.8K
3.8K

You might also read

Related Articles

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

Sort by
Same author

Confidence-based progress-driven self-generated goals for skill acquisition in developmental robots.

Frontiers in psychology·2013
Same author

An intrinsic value system for developing multiple invariant representations with incremental slowness learning.

Frontiers in neurorobotics·2013
Same author

Incremental slow feature analysis: adaptive low-complexity slow feature updating from high-dimensional input streams.

Neural computation·2012
Same author

Don't forget randomness is still just a hypothesis.

Nature·2006

Related Experiment Video

Updated: Mar 18, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

8.1K

Optimal Curiosity-Driven Modular Incremental Slow Feature Analysis.

Varun Raj Kompella1, Matthew Luciw2, Marijn Frederik Stollenga3

  • 1IDSIA, SUPSI, USI, Galleria 2, Manno-Lugano 6928, Switzerland varunrajk@gmail.com.

Neural Computation
|June 28, 2016
PubMed
Summary
This summary is machine-generated.

This study introduces curiosity-driven modular incremental slow feature analysis (SFA) for artificial agents. The model enables agents to learn complex environmental regularities efficiently by prioritizing easier-to-learn features first.

Related Experiment Videos

Last Updated: Mar 18, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

8.1K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Robotics

Background:

  • Artificial agents often face high-dimensional sensory input.
  • Slow Feature Analysis (SFA) encodes spatiotemporal regularities as latent variables.
  • Previous work enabled incremental and modular SFA for exploration.

Purpose of the Study:

  • To determine the optimal exploration order for agents learning modular slow features.
  • To formalize and theoretically validate a curiosity-driven learning approach.

Main Methods:

  • Developed curiosity-driven modular incremental slow feature analysis (SFA).
  • Theorized agent exploration based on learning difficulty of SFA.
  • Utilized Schmidhuber's theory of artificial curiosity.

Main Results:

  • The proposed model theoretically predicts learning SFA in order of increasing difficulty.
  • Experimental results support the theoretical analysis.
  • Agents prioritize exploring areas with easier-to-learn features.

Conclusions:

  • Curiosity-driven exploration optimizes learning of slow features.
  • Modular incremental SFA enhances agent's understanding of complex environments.
  • The approach facilitates efficient discovery of environmental regularities.