The Correlation Theory of Brain Function

By Christoph von der Malsburg. 1994

How researchers see this paper

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

In Neuroscience

Citations in the corpus

Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving (2019, background): “It has been studied in the context of theoretical neuroscience (von der Malsburg, 1981; 1994) but also with regards to connectionist machine learning models (Hinton et al., 1984).”
On the Binding Problem in Artificial Neural Networks (2020, background): “In other words, the features that form an object are represented by neurons that fire in synchrony (Milner, 1974; von der Malsburg, 1981; Singer, 1999; see also Section 6.3).”
Tagger: Deep Unsupervised Perceptual Grouping (2016, background): “sm. Our work is primarily built upon a line of research based on the concept that the brain uses synchronization of neuronal ﬁring to bind object representations together. This view was introduced by [33] and has inspired many early works on oscillations in neural networks (see the survey [34] for a”
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].”
Learning to Relate Images (2011, background): “An illustration of mapping units is shown in Figure 1: The three variables shown in the ﬁgure interact multiplicatively, and as a result, each variable (say, z k ) can be thought of as dynamically modulating the connections between other variables in the model ( x i and y j ).”
Learning to (Learn at Test Time): RNNs with Expressive Hidden States (2024, unknown): “This idea has existed since the 1980s [20, 32, 78].”
Learning to Reason with Third-Order Tensor Products (2018, methodology): “Variations of such outer product-based Fast Weights were able to generalise in a variety of small but complex sequence problems where standard RNNs tend to perform poorly [31, 27, 40].”
Learning Optimized Features for Hierarchical Models of Invariant Object Recognition (2003, background): “This can also be phrased as an instance of a binding problem, which occurs if the association of the feature identity with the spatial position is lost (von der Malsburg 1981).”
Generalizable Relational Binding from Coarse-coded Distributed Representations (2001, background): “Perhaps the most popular solution is to imagine that binding is encoded by some kind of transient signal, such as temporal synchrony (e.g., von der Malsburg, 1981; Gray, Engel, Konig, & Singer, 1992; Hummel & Holyoak, 1997).”
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).”
Linear Transformers Are Secretly Fast Weight Programmers (2021, methodology): “This concept was called synaptic modulation (von der Malsburg, 1981), a method for variable binding in neural networks (see e.g. the recent survey by Greff et al. (2020)), or dynamic connections (Feldman, 1982).”
Guided Search 4.0: Current Progress With a Model of Visual Search (2007, background): “The critical difference between preattentive search tasks and serial tasks was that the serial tasks required a serial “binding” step (Treisman, 1996; von der Malsburg, 1981).”
Deep Nets: What have They Ever Done for Vision? (2018, background): “Understanding neural circuits will also require understanding their dynamics and how this can change based on a host of possible mechanisms such as rapidly changing synapses (Von Der Malsburg, 1994).”