Related Experiment Video
Updated: May 20, 2026

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine
Published on: October 27, 2016
Learning in fully recurrent neural networks by approaching tangent planes to constraint surfaces
Abstract:
In this paper we present a new variant of the online real time recurrent learning algorithm proposed by Williams and Zipser (1989). Whilst the original algorithm utilises gradient information to guide the search towards the minimum training error, it is very slow in most applications and often gets stuck in local minima of the search space. It is also sensitive to the choice of learning rate and requires careful tuning. The new variant adjusts weights by moving to the tangent planes to constraint surfaces. It is simple to implement and requires no parameters to be set manually. Experimental results show that this new algorithm gives significantly faster convergence whilst avoiding problems like local minima.
Related Concept Videos
Curvilinear Motion: Normal and Tangential Components
The positive direction of the t-axis aligns with the increasing position of the car along the curved path, denoted by the unit vector ut. Simultaneously, the n-axis, perpendicular to the t-axis, dissects the curved path into differential arc segments, each forming the arc of a circle with a radius of...
Linearization and Approximation
Orthogonal Trajectories
Transformation of Plane Strain
Under plane strain conditions, typical for members where one dimension significantly exceeds the others, deformations and resultant strains are...
Curvilinear Motion: Rectangular Components
As the car advances, its position evolves over time. Quantifying the car's velocity involves computing the time...
Tangent to a Curve