The processing performed by a feed-forward neural network is oft en int erpreted through use of decision hyperplanes at each layer. T he adaptation process, however, is normally explained using the picture of gradient descent of an error land scape. In thi s paper t he dynamics of t he decision hyperplanes is used as t he model of the adaptat ion process. An electro-mechanical analogy is drawn ...

A signal space partitioning technique is presented for detecting symbols transmitted through intersymbol interference channels. The decision boundary is piecewise linear and is made up of several hyperplanes. The goal here is to minimize the number of hyperplanes for a given performance measure, namely, the minimum distance between any signal and the decision boundary. Unlike in Voronoi partiti...

In the paper [8], we introduced the notions of pseudo-hyperplane and pseudoembedding of a point-line geometry and proved that every generalized quadrangle of order (s, t), 2 ≤ s <∞, has faithful pseudo-embeddings. The present paper focuses on generalized quadrangles of order (3, t). Using the computer algebra system GAP [12] and invoking some theoretical relationships between pseudo-hyperplanes...

|A signal-space detector estimates the channel input symbol based on the location of the nite-length observation signal in a multi-dimensional signal-space. The decision boundary is formed by a set of hyperplanes. The resulting detector structure consists of linear discriminant functions, threshold detectors, and a Boolean logic function. Our goal is to minimize the number of linear discriminan...

After a review on asymptotic flatness, a general discussion of asymptotic weak and strong Poincaré charges in metric gravity is given with special emphasis on the boundary conditions needed to define the proper Hamiltonian gauge transformations and to get a differentiable Dirac Hamiltonian. Lapse and shift functions are parametrized in a way which allows to identify their asymptotic parts with ...

For analysing k-variate data sets, Randles (1989) considered hyperplanes going through k− 1 data points and the origin. He then introduced an empirical angular distance between two k-variate data vectors based on the number of hyperplanes (the so-called interdirections) that separate these two points, and proposed a multivariate sign test based on those interdirections. In this paper, we presen...

We consider schemes for recursively dividing a set of geometric objects by hyperplanes until all objects are separated. Such a binary space partition, or BSP, is naturally considered as a binary tree where each internal node corresponds to a division. The goal is to choose the hyperplanes properly so that the size of the BSP, i.e., the number of resulting fragments of the objects, is minimized....

Piecewise-linear (PWL) neural networks are widely known for their amenability to digital implementation. This paper presents a new algorithm for learning in PWL networks consisting of a single hidden layer. The approach adopted is based upon constructing a continuous PWL error function and developing an efficient algorithm to minimize it. The algorithm consists of two basic stages in searching ...

Let ∆ be a symplectic dual polar space DW (2n−1, K) or a Hermitian dual polar space DH(2n − 1, K, θ), n ≥ 2. We define a class of hyperplanes of ∆ arising from its Grassmann-embedding and discuss several properties of these hyperplanes. The construction of these hyperplanes allows us to prove that there exists an ovoid of the Hermitian dual polar space DH(2n−1, K, θ) arising from its Grassmann-...

In this paper we present some theoretical results on two forms of multi-point crossover: n-point crossover and uniform crossover. This analysis extends the work from De Jong’s thesis, which dealt with disruption of n-point crossover on 2nd order hyperplanes. We present various extensions to this theory, including 1) an analysis of the disruption of n-point crossover on kth order hyperplanes; 2)...