Learning in Artificial Neural Networks: A Statistical Perspective

By Halbert White. 1989

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, background): “, 1994), unit pruning (e.g., Ivakhnenko, 1968, 1971; White, 1989; Mozer and Smolensky, 1 989; Levin et al., 1994), weight pruning, e.”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, methodology): “As the history grows, to find an M with small bitsM + bitsH , step 4 uses sequential network construction: it regularly changes M ’s size by adding or pruning units and connections [111, 112, 8, 168, 59, 107, 304, 176, 141, 92, 143, 204, 53, 296, 106, 31, 57, 185, 283].”
Deep Learning for Mortgage Risk* (2016, background): “6More precisely, a neural network can approximate arbitrarily well continuous functions on compact sets, see Hornik, Stinchcombe & White (1989) and Hornik (1991).”
Architecture Selection Strategies for Neural Networks: Application to Corporate Bond Rating Predicti (1995, methodology): “These include the irrelevant hidden unit and irrelevant input hypothesis tests (White, 1989), pruning of units via skeletonization (Mozer and Smolensky, 1990), optimal brain surgeon OBS (Hassibi and Stork, 1993), and principal components pruning PCP (Levin et al.”
Stochastic Gradient Learning in Neural Networks (1991, background): “A convergence theorem for the stochastic backpropagation algorithm for one hidden layered networks finally was formulated in (White, 1989) (theorems 3 and 4).”
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)).”
A case study on using neural networks to perform technical forecasting of forex (2000, background): “White [ 20 ] suggested that the relationship between neural networks and conventional statistical approaches for time series forecasting are complementary.”
Neural Networks and the Bias/Variance Dilemma (1992, background): “This is also the focus of the statistical sciences, so it is not surprising that statistical tools are increasingly exploited in the development and analysis of these kinds of neural models (Lippmann 1987; Barron and Barron 1988; Gallinari et al. 1988; Barron 1989; Haussler 1989a; Tishby et al. 1989”
Fully vector-quantized neural network-based code-excited nonlinear predictive speech coding (1994, background): “White, H. (1989).”
Artificial neural networks: A new method for mineral prospectivity mapping (2000, background): “Rescaled to the range [0, 1], the network output represents the Bayesian posterior probability that the input vector belongs to the class of deposits (White 1989; Richard & Lippmann 1991; Bishop 1995).”
An Incremental Gradient(-Projection) Method with Momentum Term and Adaptive Stepsize Rule (1998, background): “In the case of neural network training, various heuristic rules for choosing the stepsize have been proposed, the most popular of which entail keeping the stepsize fixed for as long as “progress” is made and decreasing the stepsize if otherwise.”