A model for visual shape recognition.

By P. Milner. 1974

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

On the Binding Problem in Artificial Neural Networks (2020, background): “A simple form of this problem in neural networks was first pointed out in Rosenblatt (1961), and has been debated in the context of neuroscience since (Milner, 1974; von der Malsburg, 1981).”
Neural Expectation Maximization (2017, background): “3 The Binding problem was ﬁrst considered in the context of Neuroscience [21, 37] and has sparked some early work in oscillatory neural networks that use synchronization as a grouping mechanism [36, 38, 24].”
Types and tokens in visual letter perception. (1989, background): “The strength of activation of a "type" detector might be used to infer the number of tokens presented (Milner, 1974); however, if activation strength interacts with factors such as stimulus quality, as most models would presume, activation strength cannot be a terribly informative cue to numerosity.”
Understanding the Nature of Face Processing Impairment in Autism: Insights From Behavioral and Electrophysiological Studies (2005, background): “Specifically, gamma activation has been proposed as the key mechanism by which the brain links together stimulus properties (e.g., Eckhorn, Reitboeck, Arndt, & Dicke, 1990; Gray, Engel, Konig, & Singer, 1990; Gray, Konig, Engel, & Singer, 1989; Milner, 1974).”
Visual synchrony affects binding and segmentation in perception (1998, background): “An attractive scheme for binding visual features into a coherent percept consists of synchronising the activity of their neural representations [3, 4, 5, 6].”
Invariant object recognition is a personalized selection of invariant features in humans, not simply explained by hierarchical feed-forward vision models (2017, background): “We believe that this discrepancy can be explained by the top-down cognitive processes involved in visual processing of the human brain which are absent from feed-forward computational models of vision 35,58,59 .”
Binding via Reconstruction Clustering (2015, background): “This problem has been debated quite extensively in the neuroscience and psychology communities perhaps starting with Milner (1974) and von der Malsburg (1981), but its existence can be traced back at least to a description by Rosenblatt (1961).”
Invariant Visual Object and Face Recognition: Neural and Computational Bases, and a Model, VisNet (2012, background): “The cognitron and neocognitron An early computational model of a hierarchical feature-based approach to object recognition, joining other early discussions of this approach (Selfridge, 1959; Sutherland, 1968; Barlow, 1972; Milner, 1974), was proposed by Fukushima (1975, 1980, 1989, 1991).”
Dynamic binding in a neural network for shape recognition. (1992, background): “The basic idea, proposed as early as 1974 by Peter Milner (Milner, 1974), is that conjunctions of attributes can be represented by synchronizing the outputs of the units (or cells) representing those attributes.”
A Century of Gestalt Psychology in Visual Perception II. Conceptual and Theoretical Foundations (2012, background): “According to an influential point of view, this is when collective representations are bound together through synchronization of oscillatory activity (Milner, 1974; von der Malsburg, 1981).”
A Century of Gestalt Psychology in Visual Perception I. Perceptual Grouping and Figure-Ground Organization (2012, background): “A radically different and quite controversial, rationale is that temporal synchrony of changes drives grouping because synchrony of neural firings is the physiological mechanism by which the brain codes all forms of grouping (e.g., Milner, 1974; von der Malsburg, 1981).”