Jove
Visualize
Contact Us

Related Concept Videos

State Space to Transfer Function01:21

State Space to Transfer Function

The conversion of state-space representation to a transfer function is a fundamental process in system analysis. It provides a method for transitioning from a time-domain description to a frequency-domain representation, which is crucial for simplifying the analysis and design of control systems.
The transformation process begins with the state-space representation, characterized by the state equation and the output equation. These equations are typically represented as:
Transfer Function to State Space01:23

Transfer Function to State Space

State-space representation is a powerful tool for simulating physical systems on digital computers, necessitating the conversion of the transfer function into state-space form. Consider an nth-order linear differential equation with constant coefficients, like those encountered in an RLC circuit. The state variables are selected as the output and its n−1 derivatives. Differentiating these variables and substituting them back into the original equation produces the state equations.
In an RLC...
Neuroplasticity01:01

Neuroplasticity

Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.
Observational Learning01:12

Observational Learning

Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning because...
Propagation of Action Potentials01:23

Propagation of Action Potentials

The propagation of an action potential refers to the process by which a nerve impulse, or "action potential," travels along a neuron.
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...
Associative Learning01:27

Associative Learning

Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...

You might also read

Related Articles

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

Sort by
Same author

Functional Logic of a Cognitive Brain System for Navigation.

Annual review of neuroscience·2026
Same author

David Sussillo.

Neuron·2026
Same author

Neuronal calcium spikes enable vector inversion in the Drosophila brain.

Cell·2025
Same author

Transfer of graded information through gated receptivity to widely broadcast signals.

bioRxiv : the preprint server for biology·2025
Same author

Improved interpretability in LFADS models using a learned, context-dependent per-trial bias.

bioRxiv : the preprint server for biology·2025
Same author

Motor cortex flexibly deploys a high-dimensional repertoire of subskills.

bioRxiv : the preprint server for biology·2025
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

Transferring learning from external to internal weights in echo-state networks with sparse connectivity.

David Sussillo1, L F Abbott

  • 1Department of Electrical Engineering, Stanford University, Stanford, California, United States of America. sussillo@stanford.edu

Plos One
|June 2, 2012
PubMed
Summary

This study introduces a "transfer of learning" method to train recurrent neural networks efficiently. This technique modifies recurrent weights using trained echo-state network output weights, simplifying network training.

Related Experiment Videos

Area of Science:

  • Computational Neuroscience
  • Machine Learning
  • Artificial Intelligence

Background:

  • Training recurrent neural networks (RNNs) by modifying internal weights is challenging.
  • Echo-state networks (ESNs) simplify training by only modifying output weights, but require output feedback, altering network architecture.

Purpose of the Study:

  • To develop methods for training RNNs without output feedback.
  • To enable efficient training of complex tasks using recurrent networks.

Main Methods:

  • Derived methods to set recurrent weights using trained ESN output weights.
  • Introduced a "transfer of learning" approach.
  • Discussed a hybrid method with online learning on both output and recurrent weights.

Main Results:

  • Achieved a recurrent network that performs tasks without output feedback.
  • Demonstrated efficient training of RNNs for complex tasks.
  • Defined "self-sensing" network state based on transfer of learning conditions.

Conclusions:

  • The "transfer of learning" method offers an efficient alternative for training RNNs.
  • The concept of "self-sensing" networks provides new insights into network dynamics and compressed sensing.