Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol 1: Foundations, vol 2: Psychological and Biological Models

By G. Kane. 1994

Subfields: Cognitive Science & Psychology

How researchers see this paper

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

In Cognitive Science & Psychology

Citations in the corpus

Effectiveness of self-supervised pre-training for speech recognition (2019, background): “Representation learning has been an active research area for more than 30 years (Hinton et al., 1986), with the goal of learning high level representations which separates different explanatory factors of the phenomena represented by the input data (LeCun et al.”
Deep learning in neural networks: An overview (2014, background): “The Deep Belief Network (DBN) is a stack of Restricted Boltzmann Machines (RBMs) (Smolensky, 1986), which in turn are Boltzmann Machines (BMs) (Hinton & Sejnowski, 1986) with a single layer of feature-detecting units; compare also Higher-Order BMs (Memisevic & Hinton, 2010).”
Stabilizing Transformers for Reinforcement Learning (2019, background): “…with other existing proposals (Krause et al., 2016; Kalchbrenner et al., 2015; Wu et al., 2016), as well as works trying to discover optimal gating by neural architecture search (Zoph & Le, 2017) More generally, gating and multiplicative interactions have a long history (Rumelhart et al., 1986).”
Learning to Match using Local and Distributed Representations of Text for Web Search (2016, background): “[13] provides an overview contrasting distributed and local representations, listing their good and bad points.”
Learning to Relate Images (2011, methodology): “Like in a standard RBM, training involves sampling z and y .”
Cross-modal Retrieval with Correspondence Autoencoder (2014, methodology): “To be brief, RBM[22] is an undirected graphical model with stochastic binary units in a vis-10 ible layer and hidden layer but without connections between the units within these two layers.”
Convolutional Bipartite Attractor Networks (2019, methodology): “ANs are deterministic variants of Markov random fields, such as the Boltzmann machine [9, 32] and exponential-family Harmonium [40], which perform a probabilistic constraint-satisfaction search.”
Joint Autoregressive and Hierarchical Priors for Learned Image Compression (2018, methodology): “This nonlinear transform coding method resembles an autoencoder [2], [3], which consists of an encoder transform from the data (in this case, pixels) to a reduced-dimensionality latent space, and a decoder, an approximate inverse function that maps latents back to pixels.”
A Survey on Electric Power Demand Forecasting: Future Trends in Smart Grids, Microgrids and Smart Buildings (2014, background): “For the so-called “standard neuron” presented by McClelland and Rumelhart, among others, and described in McClelland and Rumelhart (1986) [74], and Rumelhart and McClelland (1986) [75], the propagation rule is the weighted sum of the input values, and the output function is the identity.”
A Neural Networks Committee for the Contextual Bandit Problem (2014, methodology): “The backpropagation algorithm [25] allows calculating the gradient of the error for each neuron from the last to the first layer by minimizing a cost function.”
Constructing inferences during narrative text comprehension. (1994, unknown): “More recently, researchers have adopted connectionist architectures for computing coherence (Britton & Eisenhart, 1993; Holyoak & Thagard, 1989; Kintsch, 1988; Read & Marcus- Newhall, 1993; Rumelhart & McClelland, 1986).”
Quantum dynamics of human decision-making (2006, background): “Quantum computing theory (Nielsen & Chuang, 2000) may provide a whole new way to synthesize production rule systems (Anderson, 1993) and parallel processing systems (Rumelhart & McClelland, 1986).”
Sequence Classification Restricted Boltzmann Machines With Gated Units (2020, background): “The local energy function (4) is an extension of the standard notation of the energy function of RBMs [29].”