Neural Network Studies

By Gregg Wilensky, N. Manukian, J. Neuhaus, Natalie Rivetti. 1993

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Model Architectures

Citations in the corpus

The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks (2018, background): “In particular, such memorization is not due to overtraining [47]: it occurs early during training, and persists across different types of models and training strategies—even when the memorized data is very rare and the model size is much smaller than the size of the training data corpus.”
In silico prediction of aqueous solubility (2006, methodology): “Statistical techniques prior to 1990 were based on linear regression, but artificial neural networks began to be used as early as 1991 [79], while partial least squares statistics and descriptor selection by genetic algorithm are also employed by some researchers.”
DBSMOTE: Density-Based Synthetic Minority Over-sampling TEchnique (2012, background): “However, over-sampling techniques, which create more specific decision regions, are negatively impacted by the overfitting problem [30], while under-sampling techniques typically suppress important parts of a dataset.”
Calculation of molecular lipophilicity: state of the art and comparison of methods on more than 96000 compounds (2009, methodology): “The new experimental values allow improving the prediction power using the user-training option without retraining provided by, for example, ALOGPS, SLIPPER, KowWIN, AB/LogP, ACD/logP, XLOGP3 and some other methods, and good local models for new accurate predictions within a similar series of compou”
Critical Assessment of QSAR Models of Environmental Toxicity against Tetrahymena pyriformis: Focusing on Applicability Domain and Overfitting by Variable Selection (2008, result): “A very similar problem of overfitting has been addressed by us for the neural network method.(40) For example, some LOO results (Table 2) were overfitted by variable selection.”
A renaissance of neural networks in drug discovery (2016, methodology): “In constructing QSAR models for drug discovery using multilayer ANNs, overtraining can occur [22].”
Online chemical modeling environment (OCHEM): web platform for data storage, model development and publishing of chemical information (2011, methodology): “This method uses the correlation between ensemble responses (each molecule is represented in the space of neural network models as a vector of predictions of neural network models) as a measure of distance amid the analyzed cases for the nearest neighbor technique [22, 72].”