A new polynomial-time algorithm for linear programming
Combinatorica
Learning by choice of internal representations
Complex Systems
Hi-index | 0.00 |
We present a local perceptron-learning rule that either converges to a solution, or establishes linear nonseparability. We prove that when no solution exists, the algorithm detects this in a finite time (number of learning steps). This time is polynomial in typical cases and exponential in the worst case, when the set of patterns is nonstrictly linearly separable. The algorithm is local and has no arbitrary parameters.