Related Experiment Video
Updated: Aug 15, 2026

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy
Published on: October 14, 2017
A constructive algorithm that converges for real-valued input patterns
1Department of Anatomy, University College, London, U.K.
Abstract:
A constructive algorithm is presented which combines the architecture of Cascade Correlation and the training of perceptron-like hidden units with the specific error-correcting roles of Upstart. Convergence to zero errors is proved for any consistent classification of real-valued pattern vectors. Addition of one extra element to each pattern allows hyper-spherical decision regions and enables convergence on real-valued inputs for existing constructive algorithms. Simulations demonstrate robust convergence and economical construction of hidden units in the benchmark "N-bit parity" and "twin spirals" problems.
Related Concept Videos
Statically Indeterminate Problem Solving
Convergence of Sequences
Comparison Tests
Alternating Series and Absolute Convergence
Interval and Radius of Convergence
Convergence of Taylor Series
