A self-optimizing, nonsymmetrical neural net for content addressable memory and pattern recognition

By A. Lapedes, R. Farber. 1986

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): “Some algorithms for controlling BP step size adapt a global learning rate (Battiti, 1989; Lapedes & Farber, 1986; LeCun, Simard, & Pearlmutter, 1993; Vogl, Mangis, Rigler, Zink, & Alkon, 1988; Yu, Chen, & Cheng, 1995), while others compute individual learning rates for each weight (Jacobs, 1988;…”
Centering Neural Network Gradient Factors (1996, unknown): “Bold driver [14, 15, 16, 17].”
A Learning Algorithm for Continually Running Fully Recurrent Neural Networks (1989, background): “Algorithms for the special case of networks that settle to stable states, often regarded as associative memory networks, have been proposed by Hop(cid:12)eld (1982), Lapedes and Farber (1986), Almeida (1987), Pineda (1988), and Rohwer and Forrest (1987).”
Neural networks for the prediction and forecasting of water resource variables: a review of modelling issues and applications (2000, methodology): “The methods proposed by Lapedes and Farber (1986); Battiti (1989); Jacobs (1988) fall in the above category.”
Reviving and Improving Recurrent Back-Propagation (2018, methodology): “Back then, RBP was shown to be useful in learning content-addressable memory (CAM) models (Hopfield, 1982; 1984) and other computational neurodynamic models (Lapedes & Farber, 1986; Haykin, 1993; Chauvin & Rumelhart, 1995).”
Fixed-weight on-line learning (1999, methodology): “For instance, Lapedes and Farber [ 15 ], [16] used the optimization ability of a Hopfield-style master network to compute the synaptic weights for a second slave network.”
Neural Networks: Tricks of the Trade (2012, methodology): “Springer, Heidelberg (2012) [11] Riedmiller, M.”
Hybrid Modeling, HMM/NN Architectures, and Protein Applications (1996, methodology): “Other examples are the rnaster-sla\Te approach of Lapedes and Farber (1986) , and the sigrnoidal belief networks in Neal (1992), where NNs are used to compute the weights of another NN, or the conditional distributions of a belief network.”