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

A general framework for adaptive processing of data structures.

P Frasconi1, M Gori, A Sperduti

  • 1Dipartimento di Sistemi e Informatica, Università di Firenze, 50139 Firenze, Italy.

IEEE Transactions on Neural Networks
|February 8, 2008
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

Primary visual cortex BOLD responses to relative localization of sounds at 7T.

iScience·2026
Same author

Clinical variables associated with late-onset thrombotic and cardiovascular events, after SARS-CoV-2 infection, in a cohort of patients from the first epidemic wave: an 18-month analysis on the "Surviving-COVID" cohort from Bergamo, Italy.

Frontiers in cardiovascular medicine·2023
Same author

Dr-MUSIC: An Effective Device for Investigating Multisensory Mechanisms during Development with EEG recordings<sup></sup>.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2023
Same author

MultiTab: A Novel Portable Device to Evaluate Multisensory Skills<sup></sup>.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2023
Same author

A novel multisensory device for the assessment and rehabilitation of perceptual and attentional competencies.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2023
Same author

Task-dependent spatial processing in the visual cortex.

Human brain mapping·2023
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This research unifies adaptive models for structured information processing using directed acyclic graphs. It extends recurrent neural networks and hidden Markov models for learning complex data relationships.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Linguistics

Background:

  • Symbolic processing demands structured information, contrasting with connectionist models' simpler data structures (arrays, sequences).
  • Existing adaptive models like artificial neural nets and belief nets struggle with processing complex, structured information effectively.

Purpose of the Study:

  • To propose a unified framework for processing structured information by integrating adaptive models.
  • To extend recurrent neural networks and hidden Markov models to handle acyclic graphs with mixed data types.

Main Methods:

  • Representing data relations using directed acyclic graphs (DAGs) accommodating both numerical and categorical values.
  • Developing a framework that extends recurrent neural networks (RNNs) and hidden Markov models (HMMs) to DAGs.

Related Experiment Videos

  • Introducing recursive networks (cyclic graphs) for adaptive transductions with a recursive hidden state-space representation.

    • Main Results:

    • The proposed framework unifies symbolic and subsymbolic data processing.
    • Recursive networks are unfolded into acyclic graphs (encoding networks) for efficient processing.
    • Inference and learning algorithms are adaptable from existing artificial neural network and probabilistic graphical model approaches.

    Conclusions:

    • The framework offers a powerful approach for supervised learning of structured data transductions.
    • It enables the incorporation of both symbolic and subsymbolic data characteristics.
    • The method facilitates the inheritance of established inference and learning algorithms for enhanced model performance.