Neural and Adaptive Systems: Fundamentals Through Simulations

By K. Chen, Vladimir Kvasnicka, P. C. Kanen, Simon S. Haykin. IEEE Trans. Neural Networks, 2001

634 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/3e527f1f14e071a1d79de31aa7370f70c67d0d53

How researchers see this paper

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

In Artificial Intelligence

In Cognitive Neuroscience

In Control and Systems Engineering

Citations in the corpus

Washback to learning outcomes: a comparative study of IELTS preparation and university pre‐sessional language courses (2007, methodology): “An artificial intelligence application was chosen for this analysis: a neural network developed using NeuroSolutions 4.16 (Principe et al., 2000).”
Short-term wind power forecasting in Portugal by neural networks and wavelet transform (2011, background): “This configuration has been proven to be a universal mapper, provided that the hidden layer has enough artificial neurons [28].”
Support-Vector-Machine-Based Models for Modeling Daily Reference Evapotranspiration With Limited Climatic Data in Extreme Arid Regions (2015, background): “However, ANN have some disadvantages such as training slowly, requiring a large amount of training data, and easily getting stuck in a local minimum (Principe et al. 2000).”
Correntropy: Properties and Applications in Non-Gaussian Signal Processing (2007, methodology): “In this example, we present a correntropy extension to the Karhunen-Loeve transform that will be called the TPCA, which is widely utilized in subspace projections [15].”
Multilayer perceptron and neural networks (2009, methodology): “The momentum method [18] proposes adding a term to adjust weights.”
Short-term electricity prices forecasting in a competitive market: A neural network approach (2007, background): “This configuration has been proven to be a universal mapper, provided that the hidden layer has enough units [33].”
Energy price forecasting in the Ontario competitive power system market (2004, methodology): “vided that the number of sigmoid neurons in the hidden layer is large enough [20].”
A novel approach for olive leaf extraction through ultrasound technology : Response surface methodology versus artificial neural networks (2014, methodology): “To minimize the error in the process, changes are adjusted/investigated in the direction of conjugate gradient [32].”
Application of type-2 neuro-fuzzy modeling in stock price prediction (2012, methodology): “The given training data set is partitioned into clusters through input-similarity and output-similarity tests, and a type-2 TSK rule is derived from each cluster to form a fuzzy rule base.”
Dynamic behavioral modeling of 3G power amplifiers using real-valued time-delay neural networks (2004, neutral): “5(b).”
Focused identification of germplasm strategy (FIGS) detects wheat stem rust resistance linked to environmental variables (2011, background): “…machines (SVM) Support Vector Machines (SVM) is also a learningbased technique that maps input data to a highdimensional space, and then optimally separates it into respective classes by isolating those inputs which fall close to the data boundaries (Cortes and Vapnik 1995; Principe et al. 2000).”
An error-entropy minimization algorithm for supervised training of nonlinear adaptive systems (2002, methodology): “A TDNN with seven hidden PEs is assumed, following the suggestion in [23].”
Information Theoretic Clustering (2002, background): “We should mention that a trained perceptron makes 19 mistakes, while a one hidden layer MLP classifier makes only three mistakes [39].”
Long-term time series prediction with the NARX network: An empirical evaluation (2008, background): “Multi-step-ahead prediction and dynamic modeling are much more complex to deal with than one-step-ahead prediction, and it is believed that these are complex tasks in which ANN models play an important role, in particular recurrent neural architectures [36].”
PCA-based feature selection scheme for machine defect classification (2004, methodology): “training rule was applied, which is characterized as [27]”
Predicting standard penetration test N-value from cone penetration test data using artificial neural networks (2017, background): “It is one of the most appropriate higher-order adaptive algorithms known for minimizing the error of a neural network (Principe et al., 1999).”
An Unsupervised Ensemble Learning Method for Nonlinear Dynamic State-Space Models (2002, methodology): “In nonlinear kernel models such as the self-organizing map (SOM) (Haykin, 1998; Principe et al., 2000), the number of parameters scales exponentially with the dimension of the latent space.”