Fundamentals of Artificial Neural Networks

By M. Hassoun, N. Intrator, S. Mckay, Wolfgang Christian. 1996

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

General fuzzy min-max neural network for clustering and classification (2000, background): “They have been successfully used in many pattern recognition problems [7], [16], [29].”
Battery Health Prediction Using Fusion-Based Feature Selection and Machine Learning (2020, methodology): “Inspired by biological systems, especially the human brain, ANNs are designed to mathematically imitate this process in the nonlinear problems [77, 78].”
Active Hebbian learning algorithm to train fuzzy cognitive maps (2004, methodology): “One of the main algorithms used in unsupervised learning is the Hebbian learning algorithm [30].”
Learning surrogate models for simulation‐based optimization (2014, methodology): “Therefore, the functional forms available to kriging or ANNs could also be potential basis functions while avoiding a full set of either form in the interest of obtaining a lower-complexity surrogate.”
Critical values for 33 discordancy test variants for outliers in normal samples up to sizes 1000, and applications in quality control in Earth Sciences (2008, background): “Details on the ANN can be found in Hassoun (1995) or Haykin (1999).”
Controllability of Boolean control networks via the Perron-Frobenius theory (2012, methodology): “BNs have been studied extensively as models for simple artificial neural networks (see, e.g. Hassoun (1995)), where each neuron realizes a threshold function that attains the values zero or one.”
Asymptotic statistical theory of overtraining and cross-validation (1997, methodology): “For example, model selection methods (e.g., [23], [20], [26] and many others), regularization ([25] and others), and early stopping ([16], [ 15 ], [30], [11], [4] and others) or structural risk minimization (SRM, cf. [32]) can be applied.”
Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions (2010, background): “Information on the basic concepts of ANNs are given in many papers and textbooks (e.g. Flood and Kartam, 1994; Hassoun, 1995; Maren et al., 1990; Masters, 1993; Rojas, 1996; Bishop, 2004).”
The Climate Change Learning Curve (2007, methodology): “For a detailed discussion of neural networks, the interested reader is referred to Hassoun (1995). (16)A complete description of the algorithm used in the present analysis is available from the author. (17)A low-discrepancy sequence is an analog to a multi-dimensional uniform random number generator”
The general inefficiency of batch training for gradient descent learning (2003, methodology): “This reference does not mention the need for reducing the learning rate when accumulating changes over multiple instances, however, and the hypothesis of increased chance of convergence for batch or mini-batch is contradicted by the results in Section 4.”
COVID-19 Outbreak Prediction with Machine Learning (2020, unknown): “21 [85] : ”
k-Plane Clustering (2000, methodology): “There are many approaches to clustering such as statistical [2, 6, 9], machine learning [7, 8 ] and mathematical programming [4, 15, 16].”