Statistical aspects of neural networks

By B. D. Ripley. 1993

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

Neural networks for classification: a survey (2000, background): “Links between neural and other conventional classifiers have been illustrated by [32], [33], [74], [139], [140], [151], [175].”
Pattern recognition and neural networks (1996, background): “Predicting suitable habitat for Tsetse flies ( Ripley, 1993 ) . Financial trading (Refenes, 1995).”
Bayesian Classification With Gaussian Processes (1998, methodology): “Network(2) used two hidden units and the predictive approach (Ripley, [19])”
Machine Learning, Neural and Statistical Classification (2009, methodology): “(1990) and Ripley (1993) The dataset used by Ripley was slightly different in that the attributes were normalised to be in the range [0,1] over the whole dataset.”
A fusion model of HMM, ANN and GA for stock market forecasting (2007, methodology): “ANNs are data-driven model (White, 1989; Ripley, 1993; Cheng & Titterington, 1994), and consequently, the underlying rules in the data are not always apparent (Zhang, Patuwo, & Hu, 1998).”
Time series forecasting with neural networks: a comparative study using the air line data (2008, unknown): “Recently, statisticians have started to investigate whether NNs are useful for tackling various statistical problems (Ripley, 1993; Cheng and Titterington, 1994) and there has been particular attention to pattern recognition (Bishop, 1995; Ripley, 1996).”
A review on design, modeling and applications of computer experiments (2006, background): “ANN models have been very popular for modeling a variety of physical relationships (for a general introduction see Lippmann (1987) or Haykin (1999), for statistical perspectives see White (1989), Barron et al. (1992), Ripley (1993), or Cheng and Titterington (1994)).”
Avoiding Pitfalls in Neural Network Research (2007, background): “modeling is the same as or similar to that of statistics, and in many aspects ANNs can be treated as the nonlinear counterparts of statistical techniques [24], [28], [58], [101], [102],”
The use of backpropagating artificial neural networks in land cover classification (2003, background): “The smallest number of hidden layer nodes required is of the order of 8 for both problems, which is the number indicated by the heuristic given by Ripley ( 1993 ).”