Introduction to artificial neural systems

By J. Zurada. 1992

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

Black-Box vs. White-Box: Understanding Their Advantages and Weaknesses From a Practical Point of View (2019, background): “Artificial neural networks (ANNs) marked a milestone due their utilization of potential functional similarities between human and artificial information processing systems [16].”
Data Mining Methods for Recommender Systems (2015, background): “On the other hand ANN and the Bayesian classifier perform similarly.”
ARTIFICIAL NEURAL NETWORK APPLICATIONS IN GEOTECHNICAL ENGINEERING (2001, unknown): “Hecht-Nielsen 1990; Maren et al. 1990; Zurada 1992; Fausett 1994; Ripley 1996).”
The Prediction of Swell Percent and Swell Pressure by Using Neural Networks (2011, background): “The current interest in ANNs is largely due to their ability to mimic natural intelligence in its learning from experience [11].”
Neural networks in business: techniques and applications for the operations researcher (2000, methodology): “The weights are continually modi " ed in this manner until the total error across all training patterns is reduced below some pre-de " ned tolerance level (or the network has started to ‘ overtrain a as measured by deteriorating performance on the test set [ 8 ]).”
Survey of computational intelligence as basis to big flood management: challenges, research directions and future work (2018, methodology): “To minimize the estimated outputs’ error, BPN modifies the parameters based on the ‘generalized delta rule’ of a supervised learning process (Zurada, 1992; Hsiao, Lin, & Chiang, 2003; Zealand et al.,1999).”
Deep learning and machine vision for food processing: A survey (2021, methodology): “The output layer is used to obtain probability prediction results (Zurada, 1992).”
Recurrent least squares support vector machines (2000, background): “Depending on the field, such models are called recurrent input/output models [9], [20], [ 29 ], nonlinear output error (NOE) models [16], or parallel models [11].”
Thirty Years of Machine Learning: The Road to Pareto-Optimal Wireless Networks (2019, background): “1) Methods: Artificial neural networks [304] constitute a set of algorithms conceived by imitating the interaction amongst neurons in the human brain, which are designed to extract features for clustering and classification tasks.”
Prototype-Incorporated Emotional Neural Network (2018, background): “More important is that machines can boast of intelligence when such systems have the capability to learn (or adapt internal parameters) and upgrade its performance over time based on available experiential knowledge [9], [10]; this is analogous to learning”
Predicting phishing websites based on self-structuring neural network (2013, background): “Larger networks have a tendency to learn fast in term of training iterations required and have increased ability to avoid local minima, but they need a large number of training samples in order to reach better generalization ability [39].”
Development of gradient-enhanced kriging approximations for multidisciplinary design optimization (2003, methodology): “Jc can be calculated using the chain rule similar to that applied in the standard backpropagation algorithm[49, 17], and the following shows how to derive Jl and Jr from Jc.”