Characterization of the Sonar Signals Benchmark
Neural Processing Letters
Efficient adaptive learning for classification tasks with binary units
Neural Computation
The Minimum Number of Errors in the N-Parity and its Solution with an Incremental Neural Network
Neural Processing Letters
Hi-index | 0.00 |
We study the numerical performances of Minimerror, a recentlyintroduced learning algorithm for the perceptron that hasanalytically been shown to be optimal both on learning linearly andnonlinearly separable functions. We present its implementation onlearning linearly separable boolean functions. Numerical resultsare in excellent agreement with the theoretical predictions.