Neurocomputing: Foundations of research

By M. Jurik. 1992

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

Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges (2019, background): “This phenomenon is known to be a common problem for multitask learning, and is also related to the stability vs plasticity dilemma (Carpenter and Grossberg, 1987; Grossberg, 1988).”
Enriching Word Vectors with Subword Information (2016, background): “Learning continuous representations of words has a long history in natural language processing (Rumelhart et al., 1988).”
Conditional Random Fields as Recurrent Neural Networks (2015, methodology): “these parameters in a single iteration was described in Section 4, they can be learnt in the RNN setting using the standard back-propagation through time algorithm [48, 40].”
AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery (2015, methodology): “Training the model was done using stochastic gradient descent with the AdaDelta adaptive learning method [34], the backpropagation algorithm [35], and mini-batches of 768 examples per gradient step.”
A Bibliometric Analysis (2005, unknown): “Some of the classic works that provide an excellent introduction to the field of artificial neural networks are that of (Mclelland and Rumelhart, 1987; Lippmann, 1987; Anderson and Rosenfeld, 1989; Wasserman, 1989).”
Robust Scene Text Recognition with Automatic Rectification (2016, unknown): “The network is trained by standard back-propagation [29].”
A Survey of Artificial Cognitive Systems: Implications for the Autonomous Development of Mental Capabilities in Computational Agents (2007, background): “For an overview of the foundation of the field and a selection of seminal papers on connectionism, see Anderson's and Rosenfeld's Neurocomputing: Foundations of Research [54] and Neurocomputing 2: Directions of Research [55] .”
Optimization for Medical Image Segmentation: Theory and Practice When Evaluating With Dice Score or Jaccard Index (2020, unknown): “In order to perform gradient descent by backpropagation [17], [14] on the empirical risk (Equation (1)), we must replace a discrete loss”
Mining the customer credit using classification and regression tree and multivariate adaptive regression splines (2006, background): “90% with 234 (340) class 1 (2) customers misclassified as class 2 (1) customers.”
Unifying computers and dynamical systems using the theory of synchronous concurrent algorithms (2009, background): “O As witnessed by the many publications in this ﬁeld, neurocomputation is a very active subject area [27,40,1].”
Advanced Steel Microstructural Classification by Deep Learning Methods (2017, methodology): “Among these Deep Learning methods, Convolutional Neural Networks (CNNs) and their modification, Fully Convolutional Neural Networks (FCNNs) have been shown particularly successful for image classification and segmentation.”
Online multimodal deep similarity learning with application to image retrieval (2013, methodology): “Finally, we can adopt backpropagation [38] to update the parameters of other layers of deep networks.”
Cocaine and Chest Pain (1992, unknown): “Although for many people artificial neural networks can be considered a new area of research, which developed in the late eighties, work in this field can be traced back to more than fifty years ago [15] [16].”