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 Experiment Videos

Autonomous mental development in high dimensional context and action spaces.

Ameet Joshi1, Juyang Weng

  • 1Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI 48824, USA. joshiame@egr.msu.edu

Neural Networks : the Official Journal of the International Neural Network Society
|July 10, 2003
PubMed
Summary
This summary is machine-generated.

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

Developmental Network-2: The Autonomous Generation of Optimal Internal-Representation Hierarchy.

IEEE transactions on neural networks and learning systems·2021
Same author

Learning to recognize while learning to speak: Self-supervision and developing a speaking motor.

Neural networks : the official journal of the International Neural Network Society·2021
Same author

Emergent neural turing machine and its visual navigation.

Neural networks : the official journal of the International Neural Network Society·2018
Same author

Editorial: Representation in the Brain.

Frontiers in psychology·2018
Same author

Motivated Optimal Developmental Learning for Sequential Tasks Without Using Rigid Time-Discounts.

IEEE transactions on neural networks and learning systems·2018
Same author

Modulation for emergent networks: serotonin and dopamine.

Neural networks : the official journal of the International Neural Network Society·2013
Same journal

A boundary-regularization-enhanced video anomaly detection network based on context-adaptive spatio-temporal conditional diffusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

MT<sup>2</sup>-CSD and LLM-CRAN: A new dataset and an LLM-based multi-semantic knowledge fusion model for conversational stance detection.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

TriAlignNet: A triple-path cross-modality alignment framework for multimodal time series forecasting.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study introduces new algorithms for robot autonomous mental development (AMD), enabling machines to learn complex tasks with high-dimensional inputs and outputs. These methods are crucial for advancing humanoid robot capabilities in perception and action.

Area of Science:

  • Robotics
  • Artificial Intelligence
  • Machine Learning

Background:

  • Autonomous Mental Development (AMD) represents a paradigm shift in creating intelligent machines, moving from manual programming to self-directed learning.
  • The SAIL project focuses on developing humanoid robots capable of integrated perception, action, and locomotion through autonomous learning.
  • Existing AMD approaches face challenges with high-dimensional action and context spaces, hindering complex task acquisition.

Purpose of the Study:

  • To address the challenge of high-dimensional action and context spaces in Autonomous Mental Development for humanoid robots.
  • To introduce and evaluate novel learning algorithms designed for complex, high-dimensional robotic systems.
  • To demonstrate the application of these algorithms in autonomous speech production learning for robots.

Related Experiment Videos

Main Methods:

  • Development and implementation of two new learning algorithms: Direct Update on Direction Cosines (DUDC) and High-Dimensional Conjugate Gradient Search (HCGS).
  • Testing and analysis of the convergence properties of DUDC and HCGS in high-dimensional action and perception spaces.
  • Application of the algorithms within a reinforcement learning framework for autonomous speech production in a humanoid robot.

Main Results:

  • The study presents the first investigation into high-dimensional numeric action spaces coupled with high-dimensional perception spaces under the AMD paradigm.
  • Both DUDC and HCGS algorithms demonstrate effectiveness in handling complex learning tasks.
  • Successful autonomous learning of speech production is achieved, showcasing the practical utility of the developed methods.

Conclusions:

  • The developed algorithms (DUDC and HCGS) offer a viable solution for enabling Autonomous Mental Development in robots with complex, high-dimensional capabilities.
  • This work advances the field of machine intelligence by providing new tools for creating more autonomous and adaptable humanoid robots.
  • The successful application to speech production learning highlights the potential for broader applications in robot skill acquisition and human-robot interaction.