A random sampling based algorithm for learning the intersection of half-spaces (1997) [18 citations — 2 self]
Abstract:
We present an algorithm for learning the intersection of half-spaces in n dimensions. Over nearlyuniform distributions, it runs in polynomial time for up to O(log n = log log n) half-spaces or, more generally, for any number of half-spaces whose normal vectors lie in an O(log n = log log n) dimensional subspace. Over less restricted "non-concentrated " distributions it runs in polynomial time for a constant number of half-spaces. This generalizes an earlier result of Blum and Kannan [4]. The algorithm is simple and is based on random sampling. 1
Citations
| 782 | Geometric Algorithms and Combinatorial Optimization. Algorithms and Combinatorics 2. SpringerVerlag – Grötschel, Lovász, et al. - 1988 |
| 363 | Perceptrons : An Introduction to Computational Geometry – Papert - 1969 |
| 189 | Principles of Neurodynamics – Rosenblatt - 1962 |
| 40 | S.: A Polynomial-Time Algorithm for Learning Noisy Linear Threshold Functions – Blum, Frieze, et al. - 1996 |
| 39 | On the complexity of polyhedral separability – Megiddo - 1988 |
| 35 | unknown title – Kannan, Lovasz, et al. - 1997 |
| 30 | Composite geometric concepts and polynomial predictability – Long, Warmuth - 1991 |
| 28 | A random polynomial time algorithm for estimating the volumes of convex bodies – Dyer, Frieze, et al. - 1989 |
| 20 | On learning a union of half spaces – Baum - 1990 |
| 13 | Learning an intersection of k halfspaces over a uniform distribution – Blum, Kannan - 1993 |
| 11 | Polynomial time algorithms for learning neural nets – Baum - 1990 |
| 1 | Training a 3-node neural network is NP -hard. Neural Networks – Blum, Rivest - 1992 |

