Principles of neurodynamics

By A. Mullin, F. Rosenblatt. 1962

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

Relational inductive biases, deep learning, and graph networks (2018, background): “Perhaps the most common building block is a fully connected layer (Rosenblatt, 1961).”
The Symbol Grounding Problem (1990, neutral): “An early rival to the symbolic model of mind appeared [36], was overcome by symbolic AI [27] and has recently re-appeared in a stronger form that is currently vying with AI to be the general theory of cognition and behavior [23] [39].”
Learning values across many orders of magnitude (2016, background): “ze and the loss, and it is hard to pick suitable step sizes when nothing is known about the magnitude of the loss. An important special case is when f is a neural network [McCulloch and Pitts, 1943, Rosenblatt, 1962], which are often trained with a form of SGD [Rumelhart et al., 1986], with hyperpar”
Rethinking eliminative connectionism. (1998, background): “Instead, what I have shown is that multilayer feedforward networks inherit— unchanged—the Achilles heel of their two-layer predecessors (perceptrons), described over 35 years ago by Rosenblatt (1962):”
A Survey of Quantization Methods for Efficient Neural Network Inference (2021, neutral): “From a historical perspective, we should note that the original idea of STE can be traced back to the seminal work of [202, 203], where an identity operator was used to approximate gradient from the binary neurons.”
Gaussian Process Kernels for Pattern Discovery and Extrapolation (2013, methodology): “The first machine learning models, such as the perceptron (Rosenblatt, 1962), were based on a simple model of a neuron (McCulloch & Pitts, 1943). Papers such as Rumelhart et al. (1986) inspired hope that it would be possible to develop intelligent agents with models like neural networks, which could”
Extending Machine Language Models toward Human-Level Language Understanding (2019, background): “They were ﬁrst articulated in the 1950s (2) and further developed in the 1980s in the Parallel Distributed Processing (PDP) framework for modeling cognition (3).”