Neural networks: applications in industry, business and science

By Bernard Widrow, David E. Rumelhart, Michael A. Lehr. 1994

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

Deep learning in neural networks: An overview (2014, neutral): “5 Fast Graphics Processing Units (GPUs) for DL in NNs While the previous millennium saw several attempts at creating fast NN-specific hardware (e.g., Jackel et al., 1990; Faggin, 1992; Ramacher et al., 1993; Widrow et al., 1994; Heemskerk, 1995; Korkin et al., 1997; Urlbe, 1999), and at exploiting s”
Extracting comprehensible models from trained neural networks (1996, background): “Algorithms that are able to learn inductively from examples have been applied to numerous difficult, real-world problems of practical interest (Widrow et al., 1994; Langley & Simon, 1995).”
Neural networks for classification: a survey (2000, background): “Neural networks have been successfully applied to a variety of real world classification tasks in industry, business and science [186].”
Short term wind speed forecasting in La Venta, Oaxaca, México, using artificial neural networks (2009, background): “Its use has been successful in a great variety of tasks in diverse fields such as industrial processes, sciences and business [1].”
An introduction to the use of neural networks in control systems (2002, methodology): “The Levenberg-Marquardt algorithm is very efficient for training small to medium-size networks, and it uses a backpropagation procedure that is very similar to the one given by Eq. ( 30 ).12”
Credit rating analysis with support vector machines and neural networks: a market comparative study (2004, background): “Backpropagation neural networks have been extremely popular for their unique learning capability [48] and have been shown to perform well in different applications in our previous research such as medical application [43] and game playing [4].”
SEMINT: A tool for identifying attribute correspondences in heterogeneous databases using neural networks (2000, methodology): “Neural networks have emerged as a powerful pattern recognition technique due to the development of more powerful hardware and ecient algorithms [29] and have been used in a wide range of application [40].”