Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Rigid Body Equilibrium Problems - II

Rigid Body Equilibrium Problems - II

A rigid body is in static equilibrium when the net force and the net torque acting on the system are equal to zero.
Consider two children sitting on a seesaw, which has negligible mass. The first child has a mass (m1) of 26 kg and sits at point A, which is 1.6 meters (r1) from the pivot point B; the second child has a mass (m2) of 32 kg and sits at point C. How far from the pivot point B should the second child sit (r2) to balance the seesaw?

Apparent Weight

Apparent Weight

True weight is the measure of the gravitational force acting on an object. However, if the object accelerates, its measured weight is different from its true weight. Similar observations can be made when the object is submerged in water. An object's weight in water is its apparent weight, which is equal to the difference between its true weight and the buoyant forces.
Consider a person standing on a bathroom scale inside an elevator. If the scale is accurate at rest, its reading equals the...

Static Equilibrium - II

Static Equilibrium - II

Static equilibrium is a special case in mechanics that is very important in everyday life. It occurs when the net force and the net torque on an object or system are both zero. This means that both the linear and angular accelerations are zero. Thus, the object is at rest, or its center of mass is moving at a constant velocity. However, this does not mean that no forces are acting on the object within the system. In fact, there are very few scenarios on Earth in which no forces are acting upon...

Mass and Weight

Mass and Weight

Mass and weight are often used interchangeably in everyday conversation. For example, medical records often show our weight in kilograms, but never in the correct units of newtons. In physics, however, there is an important distinction. Weight is the pull of the Earth on an object. It depends on the distance from the center of the Earth. Weight dramatically varies if we leave the Earth's surface, unlike mass, which does not vary with location. On the Moon, for example, the acceleration due to...

Mass and Weight

Mass and Weight

Mass and weight are often used interchangeably in everyday conversation. For example, medical records often show our weight in kilograms, but never in the correct units of newtons. In physics, however, there is an important distinction. Weight is the pull of the Earth on an object. It depends on the distance from the center of the Earth. Weight dramatically varies if we leave the Earth's surface, unlike mass, which does not vary with location. On the Moon, for example, the acceleration due to...

Weighted Mean

Weighted Mean

While taking the arithmetic, geometric, or harmonic mean of a sample data set, equal importance is assigned to all the data points. However, all the values may not always be equally important in some data sets. An intrinsic bias might make it more important to give more weightage to specific values over others.
For example, consider the number of goals scored in the matches of a tournament. While computing the average number of goals scored in the tournament, it may be more important to...

You might also read

Related Articles

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

Sort by

Same author

Clinical and radiographic outcomes of the mobility total ankle arthroplasty system: early results from a prospective multicenter study.

Foot & ankle international·2013

Same author

Total knee arthroplasty in Paget's disease: technical problems and results.

Orthopedics·1999

Same author

Surgical exposures in revision total knee arthroplasty.

The Journal of the American Academy of Orthopaedic Surgeons·1998

Same author

The role of diagnostic block in the management of Morton's neuroma.

Canadian journal of surgery. Journal canadien de chirurgie·1998

Same author

Periprosthetic hip and knee fractures: the scope of the problem.

Instructional course lectures·1998

Same author

Diagnosis of infection following total hip arthroplasty.

Instructional course lectures·1998

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

Search research articles

Related Experiment Video

Updated: Jul 7, 2026

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

Published on: June 1, 2015

Fixed-weight on-line learning.

A S Younger¹, P R Conwell, N E Cotter

¹Physics Department, University of Utah, Salt Lake City, UT 84112, USA.

IEEE Transactions on Neural Networks

|February 7, 2008

Summary

This summary is machine-generated.

This study introduces novel artificial neural networks that use recurrent loops for dynamic learning, akin to short-term memory. These networks adapt online without weight changes, offering a new paradigm for adaptive systems.

More Related Videos

Mimicking a Space Mission to Mars Using Hindlimb Unloading and Partial Weight Bearing in Rats

Mimicking a Space Mission to Mars Using Hindlimb Unloading and Partial Weight Bearing in Rats

Published on: April 4, 2019

Related Experiment Videos

Last Updated: Jul 7, 2026

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

Published on: June 1, 2015

Mimicking a Space Mission to Mars Using Hindlimb Unloading and Partial Weight Bearing in Rats

Mimicking a Space Mission to Mars Using Hindlimb Unloading and Partial Weight Bearing in Rats

Published on: April 4, 2019

Area of Science:

Artificial Intelligence
Computational Neuroscience

Background:

Conventional artificial neural networks (ANNs) rely on synaptic weights for long-term memory to perform functional mappings.
A need exists for ANNs capable of dynamic, online learning without constant weight modification.

Purpose of the Study:

To present a novel ANN design utilizing recurrent signal loops for knowledge storage, analogous to short-term memory.
To develop networks where synaptic weights encode learning algorithms, enabling dynamic adaptation.

Main Methods:

Introduced higher-order fixed-weight learning networks with embedded learning algorithms (backpropagation or gradient-descent).
Designed networks with recurrent signal loops for dynamic knowledge storage.
Conducted empirical tests on discrete (Boolean) and continuous function sets.

Main Results:

Networks successfully learned diverse functional mappings online without synaptic weight alteration.
Demonstrated robustness to synaptic weight perturbations, except for recurrent connections (0.5% tolerance).
Network cost scaled proportionally with the number of synapses.

Conclusions:

The proposed fixed-weight learning networks offer a dynamic, adaptive learning capability.
Recurrent connections are crucial for short-term memory storage but require precise tuning.
This approach advances adaptive dynamic systems and opens avenues for meta-learning analysis.