The perceptron: a probabilistic model for information storage and organization in the brain.

By F. Rosenblatt. 1958

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

What can the brain teach us about building artificial intelligence? (2016, methodology): “apid model building Since their inception, neural networks models have stressed the importance of learning. There are many learning algorithms for neural networks, including the perceptron algorithm (Rosenblatt, 1958), Hebbian learning (Hebb, 1949), the BCM rule (Bienenstock, Cooper, & Munro, 19”
Search-based structured prediction (2009, positive): “The structured perceptron is an extension of the standard perceptron [46] to structured prediction [8].”
Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms (2002, methodology): “The algorithms are based on the perceptron algorithm (Rosenblatt 58), and the voted or averaged versions of the perceptron described in (Freund & Schapire 99).”
Kernel Mean Embedding of Distributions: A Review and Beyonds (2016, methodology): “Many classical learning algorithms—such as the perceptron (Rosenblatt 1958), support vector machine (SVM) (Cortes and Vapnik 1995), and principal component analysis (PCA) (Pearson 1901, Hotelling 1933)—employ data instances, e.g., x,x′ ∈ X , only through an inner product 〈x,x′〉, which basically is…”
Differentially-Private "Draw and Discard" Machine Learning (2018, background): “Logistic regression [10] and neural networks [45], introduced over half a century ago, follow a now-familiar paradigm of reading training data from the local disk and adjusting model weights until certain convergence criteria are met.”
Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptron (2018, methodology): “In this section, we use the strong growth property of the squared-hinge function in order to prove a bound on the number of mistakes made by the perceptron algorithm [29] using a squared-hinge loss.”
Property Inference Attacks on Fully Connected Neural Networks using Permutation Invariant Representations (2018, background): “The most commonly used layers are fully connected layers which are composed of multiple computational units called perceptrons (or neurons) [36], each possessing a multiplicative weight”
Deep learning in neural networks: An overview (2014, neutral): “.16, 5.17, 5.18), in particular, GPU-MPCNNs (Sec. 5.18). 5.1 1940s and Earlier NN research started in the 1940s (e.g., McCulloch and Pitts, 1943; Hebb, 1949); compare also later work on learning NNs (Rosenblatt, 1958, 1962; Widrow and Hoff, 1962; Grossberg, 1969; Kohonen, 1972; von der Malsburg, 197”
An overview of deep learning in medical imaging focusing on MRI (2018, methodology): “network is the multilayer perceptron, or feedforward neural network, originating from the work of Rosenblatt in the 1950s [51].”
Re-evaluating circuit mechanisms underlying pattern separation (2019, neutral): “This enables a downstream decoder, such as a perceptron (Rosenblatt, 1958) or support vector machine (Cortes and Vapnik, 1995), to better classify input patterns into arbitrary associations using supervised learning.”
Simplifying Graph Convolutional Networks (2019, background): “, Tianyi Zhang <tz58@cornell.edu>. linear Perceptron (Rosenblatt, 1958) motivated the development of the more complex but also more expressive neural network (or multi-layer Perceptrons, MLPs) (Rosenblatt, 1961).”
Behaviour Suite for Reinforcement Learning (2019, background): “Many of the key ideas for deep learning have been around, and with successful demonstrations, for many years before the modern deep learning explosion (Rosenblatt, 1958; Ivakhnenko, 1968; Fukushima, 1979).”
Breaking the Curse of Dimensionality with Convex Neural Networks (2014, background): “o as the rectiﬁed linear unit , has seen considerable recent empirical success (Nair and Hinton, 2010; Krizhevsky et al., 2012), while the case α = 0 (hard thresholds) has some historical importance (Rosenblatt, 1958). The goal of this section is to specialize the results from Section 2 to this part”
Deep learning for computational biology (2016, neutral): “…2015), specificities of DNA-and RNA-binding proteins Box 1 : Artificial Neural Network An artificial neural network, initially inspired by neural networks in the brain (McCulloch & Pitts, 1943 ; Farley & Clark, 1954 ; Rosenblatt, 1958 ), consists of layers of interconnected compute units (neurons).”
1D Convolutional Neural Networks and Applications: A Survey (2019, background): “The concept of ‘‘Perceptron”, was proposed by Frank Rosenblatt in his seminal work [4].”