Autoassociative neural networks

By Mark A. Kramer. 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

Meta-Consolidation for Continual Learning (2020, background): “Interestingly, many years ago, [64] used auto-associative neural networks [40] to study connections between sleep-induced consolidation and reduction in catastrophic forgetting.”
Survey on data-driven industrial process monitoring and diagnosis (2012, methodology): “Nonlinear extensions of PCA and PLS models were developed about 20 years ago (Kramer, 1992; Dong & McAvoy, 1996; Wold, 1992; Qin & McAvoy, 1992).”
Understanding Deep Learning Techniques for Image Segmentation (2019, background): “e function represents a linear layer in tradition LSTM and a convolutional layer in convolutional LSTM Autoencoders : Autoencoders have been around since the introduction of auto-associative networks [102] for multi-layer perceptron. The principle behind autoencoders is to encode raw inputs into a l”
Collaborative Filtering with Stacked Denoising AutoEncoders and Sparse Inputs (2015, methodology): “Autoencoders are feed-forward neural networks popularized by Kramer [7].”
Estimation of free-swelling index based on coal analysis using multivariable regression and artifici (2011, background): “Similar weighted connections exist between nodes of hidden layers, as well as between the last hidden layer and nodes in the output layer [18–23].”
An Overview of Intelligent Fault Detection in Systems and Structures (2004, background): “The alternative for sensors like accelerometers which cannot accommodate substantial electronics, is to allow the sensors to monitor each other as described, for example, in Kramers [10,11].”
Sensor validation using principal component analysis (2005, methodology): “The first is commonly adopted in the process control community and can be found described in [4, 5, 8]; it relies on redundancy of information between different sensors.”
Linear and nonlinear methods for brain-computer interfaces (2003, methodology): “Autoassociative neural networks are nonlinear, feedforward networks trained using the standard error backpropagation algorithm to minimize the squared error between the output and the input to the network [12], [13].”