Artificial neural networks: fundamentals, computing, design, and application.

By I. Basheer, M. Hajmeer. 2000

2,957 citations recorded by the source corpus.

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

Citations in the corpus

Black-Box vs. White-Box: Understanding Their Advantages and Weaknesses From a Practical Point of View (2019, background): “ANNs are based a set of artificial neurons, which are connected by using a weight that adjusts as learning proceeds [17].”
Modeling groundwater fluctuations by three different evolutionary neural network techniques using hydroclimatic data (2017, positive): “In these types of NNs, optimization of the weights is made by backward propagation of the error during training or learning phase (Basheer and Hajmeer 2000; Mukherjee and Routroy 2012).”
Predicting phishing websites based on self-structuring neural network (2013, methodology): “• Identical designing steps: The same principles, scheme and methodological steps are employed in designing ANN in all domains [12].”
EEG signals classification using the K-means clustering and a multilayer perceptron neural network model (2011, methodology): “Each wji weight is adjusted to minimize the value E depending on the training algorithm adopted (Basheer & Hajmeer, 2000; Haykin, 2008; Subasi, 2007; Ubeyli, 2009a).”
EEG signal classification using wavelet feature extraction and a mixture of expert model (2007, methodology): “How w ji is adjusted depends on the training algorithm adopted (Basheer & Hajmeer, 2000; Chaudhuri & Bhattacharya, 2000; Haykin, 1994).”
Application of GA-BP Neural Network Optimized by Grey Verhulst Model around Settlement Prediction of Foundation Pit (2021, positive): “…engineering and plays an important role in predicting and distinguishing, while the BP neural network is one of the most widely used ANN in engineering ﬁ elds for its strong ability of self-learning, information processing, nonlinear mapping, error feedback adjustment, and fault tolerance [49, 50].”
Deep-learning: investigating deep neural networks hyper-parameters and comparison of performance to shallow methods for modeling bioactivity data (2017, background): “An DNN consists of multiple fully-connected layers: an input layer, one or multiple hidden layers and a single output layer [27].”
Artificial neural networks in medical diagnosis (2013, methodology): “Here we will give only a brief description of the learning process; more details are provided for example in the review by (Basheer and Hajmeer 2000).”
Evaluating calibration methods for predicting soil available nutrients using hyperspectral VNIR data (2018, methodology): “The learning rate was set as 0.2, the performance (mse) goal as 0.01 and the maximum number of training epochs as 1000 (Basheer and Hajmeer, 2000).”