Separating Points by Parallel Hyperplanes - Characterization Problem

نویسندگان

  • Silvia Ghilezan
  • Jovanka Pantovic
  • Jovisa D. Zunic
چکیده

This paper deals with partitions of a discrete set S of points in a d-dimensional space, by h parallel hyperplanes. Such partitions are in a direct correspondence with multilinear threshold functions which appear in the theory of neural networks and multivalued logic. The characterization (encoding) problem is studied. We show that a unique characterization (encoding) of such multilinear partitions of S = {0, 1,..., m-1}d is possible within theta(h x d2 x log m) bit rate per encoded partition. The proposed characterization (code) consists of (d + 1) x (h + 1) discrete moments having the order no bigger than 1. The obtained bit rate is evaluated depending on the mutual relations between h, d, and m. The optimality is reached in some cases.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Constructively Learning a Near-Minimal Neural Network Architecture

AbetractRather than iteratively manually examining a variety of pre-specified architectures, a constructive learning algorithm dynamically creates a problem-specific neural network architecture. Here we present an revised version of our parallel constructive neural network learning algorithm which constructs such an architecture. The three steps of searching for points on separating hyperplanes...

متن کامل

Separating points by axis-parallel lines

We study the problem of separating n points in the plane, no two of whi h have the same xor yoordinate, using a minimum number of verti al and horizontal lines avoiding the points, so that ea h ell of the subdivision ontains at most one point. Extending previous NP-hardness results due to Freimer et al. we prove that this problem and some variants of it are APX-hard. We give a 2-approximation a...

متن کامل

Efficiency Analysis Based on Separating Hyperplanes for Improving Discrimination among DMUs

Data envelopment analysis (DEA) is a non-parametric method for evaluating the relative technical efficiency for each member of a set of peer decision making units (DMUs) with multiple inputs and multiple outputs. The original DEA models use positive input and output variables that are measured on a ratio scale, but these models do not apply to the variables in which interval scale data can appe...

متن کامل

On Covering Points with Minimum Turns

For the rectilinear version of the problem in which the lines must be axis-parallel, • Hassin and Megiddo (1991) observed that the problem in R reduces to vertex cover in bipartite graphs and hence is solvable in polynomial time, and proved that the problem in R in NP-hard by a reduction from 3SAT, • Gaur and Bhattacharya (2007) presented a (d − 1)approximation algorithm for the problem in R fo...

متن کامل

NOKMeans: Non-Orthogonal K-means Hashing

Finding nearest neighbor points in a large scale high dimensional data set is of wide interest in computer vision. One popular and efficient approach is to encode each data point as a binary code in Hamming space using separating hyperplanes. One condition which is often implicitly assumed is that the separating hyperplanes should be mutually orthogonal. With the aim of increasing the represent...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • IEEE transactions on neural networks

دوره 18 5  شماره 

صفحات  -

تاریخ انتشار 2007