Results 1  10
of
740
Deep Sparse Rectifier Neural Networks
"... While logistic sigmoid neurons are more biologically plausible than hyperbolic tangent neurons, the latter work better for training multilayer neural networks. This paper shows that rectifying neurons are an even better model of biological neurons and yield equal or better performance than hyperbol ..."
Abstract

Cited by 57 (17 self)
 Add to MetaCart
While logistic sigmoid neurons are more biologically plausible than hyperbolic tangent neurons, the latter work better for training multilayer neural networks. This paper shows that rectifying neurons are an even better model of biological neurons and yield equal or better performance than
SRB measures for partially hyperbolic systems whose central direction is mostly expanding
, 2000
"... We construct SinaiRuelleBowen (SRB) measures supported on partially hyperbolic sets of diffeomorphisms  the tangent bundle splits into two invariant subbundles, one of which is uniformly contracting  under the assumption that the complementary subbundle is nonuniformly expanding. If the r ..."
Abstract

Cited by 197 (44 self)
 Add to MetaCart
We construct SinaiRuelleBowen (SRB) measures supported on partially hyperbolic sets of diffeomorphisms  the tangent bundle splits into two invariant subbundles, one of which is uniformly contracting  under the assumption that the complementary subbundle is nonuniformly expanding
High Speed VLSI Implementation of the Hyperbolic Tangent Sigmoid Function
"... The hyperbolic tangent function is commonly used as the activation function in articial neural networks. In this work, two different hardware implementations for the hyperbolic tangent function are proposed. Both methods are based on the approximation of the function rather than calculating it, si ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
The hyperbolic tangent function is commonly used as the activation function in articial neural networks. In this work, two different hardware implementations for the hyperbolic tangent function are proposed. Both methods are based on the approximation of the function rather than calculating it
Symbolic dynamics for hyperbolic flows
 Amer. J. Math
, 1973
"... Let/, {t e R) be a differentiable flow on a compact manifold M. A compact invariant set A containing no fixed points is called hyperbolic if the tangent bundle restricted to A can be written as the Whitney sum of three Zyjinvariant continuous subbundles TAM = E + Es + Eu, where Eis the onedimensi ..."
Abstract

Cited by 118 (0 self)
 Add to MetaCart
Let/, {t e R) be a differentiable flow on a compact manifold M. A compact invariant set A containing no fixed points is called hyperbolic if the tangent bundle restricted to A can be written as the Whitney sum of three Zyjinvariant continuous subbundles TAM = E + Es + Eu, where Eis the one
Tangent Tangent Plot
"... Abstract — In this paper, a novel signal processing method is suggested for classifying epileptic seizures. To this end, first the Tangent and Hyperbolic Tangent of signals are calculated and then are classified into two classes: normal (or interictal) and ictal, using a proposed classifier. The res ..."
Abstract
 Add to MetaCart
Abstract — In this paper, a novel signal processing method is suggested for classifying epileptic seizures. To this end, first the Tangent and Hyperbolic Tangent of signals are calculated and then are classified into two classes: normal (or interictal) and ictal, using a proposed classifier
Hyperbolic Tangent Sigmoid Multilayered Perceptron, and the Adaptive Radial Basis Function Networks.
, 2000
"... Predictions on the surface finish of workpieces in electrical discharge machining (EDM) based upon physical or empirical models have been reported in the past years. However, when the change of electrode polarity has been considered, very few models have given reliable predictions. In this study, t ..."
Abstract
 Add to MetaCart
, the comparisons on predictions of surface finish for various work materials with the change of electrode polarity based upon six different neuralnetworks models and a neurofuzzy network model have been illustrated. The neuralnetwork models are the Logistic Sigmoid Multilayered Perceptron (LOGMLP
J.C.: Best practices for convolutional neural networks applied to visual document analysis
 In: Int’l Conference on Document Analysis and Recognition
, 2003
"... Neural networks are a powerful technology for classification of visual inputs arising from documents. However, there is a confusing plethora of different neural network methods that are used in the literature and in industry. This paper describes a set of concrete best practices that document analys ..."
Abstract

Cited by 201 (7 self)
 Add to MetaCart
Neural networks are a powerful technology for classification of visual inputs arising from documents. However, there is a confusing plethora of different neural network methods that are used in the literature and in industry. This paper describes a set of concrete best practices that document
CMOS VLSI Hyperbolic Tangent Function & its Derivative Circuits for Neuron Implementation
"... Abstract The hyperbolic tangent function and its derivative are key essential element in analog signal processing and especially in analog VLSI implementation of neuron of artificial neural networks. The main conditions of these types of circuits are the small silicon area, and the low power consum ..."
Abstract
 Add to MetaCart
Abstract The hyperbolic tangent function and its derivative are key essential element in analog signal processing and especially in analog VLSI implementation of neuron of artificial neural networks. The main conditions of these types of circuits are the small silicon area, and the low power
The tangent measure distributions of hyperbolic Cantor sets
 Mh. Math
, 1998
"... Tangent measure distributions were introduced by Bandt [2] and Graf [8] as a means to describe the local geometry of selfsimilar sets generated by iteration of contractive similitudes. In this paper we study the tangent measure distributions of hyperbolic Cantor sets generated by certain contract ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
Tangent measure distributions were introduced by Bandt [2] and Graf [8] as a means to describe the local geometry of selfsimilar sets generated by iteration of contractive similitudes. In this paper we study the tangent measure distributions of hyperbolic Cantor sets generated by certain
Results 1  10
of
740