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

Classification of Systems-II01:31

Classification of Systems-II

Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
Neural Circuits01:25

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Classification of Systems-I01:26

Classification of Systems-I

Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Linear time-invariant Systems01:23

Linear time-invariant Systems

A system is linear if it displays the characteristics of homogeneity and additivity, together termed the superposition property. This principle is fundamental in all linear systems. Linear time-invariant (LTI) systems include systems with linear elements and constant parameters.
The input-output behavior of an LTI system can be fully defined by its response to an impulsive excitation at its input. Once this impulse response is known, the system's reaction to any other input can be calculated...
Understanding Memory01:19

Understanding Memory

Memory is the retention of information or experiences over time, facilitated through three main processes: encoding, storage, and retrieval. Encoding is the process of inputting information into the memory system. For instance, when listening to a lecture, watching a play, reading a book, or having a conversation, the brain is actively encoding information. This initial stage involves transforming sensory input into a form that can be processed and stored by the brain. Various factors, such as...
Higher Mental Functions of Brain: Learning and Memory01:26

Higher Mental Functions of Brain: Learning and Memory

Memory is one of the most vital higher mental functions of the brain. Memory is closely related to learning because it enables us to retain information and experiences from our past to use them in our present life. It also helps us to remember facts, events, and skills, such as riding a bike or swimming. There are two types of memory — declarative memory, which involves memorizing facts or events, and procedural memory, which enables us to remember how to do something like writing or playing an...

You might also read

Related Articles

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

Sort by
Same author

Oncilla Robot: A Versatile Open-Source Quadruped Research Robot With Compliant Pantograph Legs.

Frontiers in robotics and AI·2021
Same author

A Differentiable Physics Engine for Deep Learning in Robotics.

Frontiers in neurorobotics·2019
Same author

Online Training of an Opto-Electronic Reservoir Computer Applied to Real-Time Channel Equalization.

IEEE transactions on neural networks and learning systems·2017
Same author

Embodiment of Learning in Electro-Optical Signal Processors.

Physical review letters·2016
Same author

Trainable hardware for dynamical computing using error backpropagation through physical media.

Nature communications·2015
Same author

On learning navigation behaviors for small mobile robots with reservoir computing architectures.

IEEE transactions on neural networks and learning systems·2015

Related Experiment Videos

Memory in linear recurrent neural networks in continuous time.

Michiel Hermans1, Benjamin Schrauwen

  • 1Department of Electronics and Information Systems, Ghent University, Sint-Pietersnieuwstraat 41, 9000 Ghent, Belgium. Michiel.Hermans@ugent.be

Neural Networks : the Official Journal of the International Neural Network Society
|September 15, 2009
PubMed
Summary
This summary is machine-generated.

This study analyzes memory in continuous-time physical reservoir computing systems. It develops a model showing that specific eigenvalue distributions and orthogonal matrices enhance memory performance and robustness.

Related Experiment Videos

Area of Science:

  • Computational neuroscience
  • Machine learning
  • Complex systems

Background:

  • Reservoir Computing (RC) typically uses digital, discrete-time recurrent neural networks.
  • A recent trend employs physical dynamical systems, operating in continuous time, for RC implementation.
  • This shift necessitates understanding memory properties in continuous-time systems.

Purpose of the Study:

  • To analytically model and investigate memory properties of continuous-time linear dynamical systems in Reservoir Computing.
  • To compare the memory performance of different reservoir configurations in the continuous-time domain.

Main Methods:

  • Developed an analytical model for calculating the memory function of continuous-time linear dynamical systems (networks of linear leaky integrator neurons).
  • Evaluated memory properties using random connection matrices with shifted eigenvalue spectra.
  • Transformed discrete-time reservoir designs (uniform eigenvalue spread on unit disk, orthogonal matrices) to the continuous-time domain for analysis.

Main Results:

  • Random connection matrices with shifted eigenvalues exhibit poor memory performance.
  • Continuous-time reservoirs based on uniform eigenvalue spread on the unit disk show improved memory properties compared to random configurations.
  • Continuous-time reservoirs based on orthogonal matrices demonstrate robustness to noise and tunable memory properties.

Conclusions:

  • The analytical model provides crucial insights for designing effective continuous-time reservoir networks.
  • Specific eigenvalue distributions and orthogonal matrix properties are key for optimizing memory in physical Reservoir Computing systems.