Neural Networks: A Comprehensive Foundation (3rd Edition)

By Simon S. Haykin. 2007

879 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/c2d7a195fa530553a4fa89ccc0e1b27658c5c7cd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Prediction of sweetness and amino acid content in soybean crops from hyperspectral imagery (2007, background): “The basic MLP network architecture is composed of the input layer, one hidden layer, and the output layer, sequentially interconnected in a feed-forward way (Haykin, 1999).”
Emotional speech recognition: Resources, features, and methods (2006, methodology): “An interesting property of ANNs is that by changing the number of hidden nodes and hidden layers we control the non-linear decision boundaries between the emotional states (Haykin, 1998; van der Heijden et al., 2004).”
Tikhonov-Type Regularization for Restricted Boltzmann Machines (2012, methodology): “Along this line of research, we investigate a Tikhonov-type regularization (see, e.g., [1, 9]) by which we refer to regularizing the derivative of either an approximating function or a function related to it.”
Extracting semantic representations from word co-occurrence statistics: A computational study (2007, methodology): “However, for the purposes of this paper we shall assume that if we can come up with suitable formulations of the three stages independently, then they can be combined into a consistent and coherent on-line whole using existing connectionist techniques (e.g., Bishop, 1995; Haykin, 1999), and any cons”
Kernel Methods in Finance (2008, methodology): “, 2002), as well as relevant book chapters in (Haykin, 1999; Gentle et al., 2004; Bishop, 2006), and a number of recent collections and overviews on associated topics such as (Müller et al.”
Beyond Covariance: Feature Representation with Nonlinear Kernel Matrices (2015, methodology): “A direct application of Micchelli’s Theorem (1986) [9] gives the following result for our case.”
The Kernel Least-Mean-Square Algorithm (2008, unknown): “In the framework of stochastic projection, the space spanned by { ( )} i u Φ is so large that the projection error of the desired signal n y could be very small [32], as is well known from Cover’s theorem [10].”