How patterned neural connections can be set up by self-organization

By David J. Willshaw, Christoph von der Malsburg. 1976

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

Deep learning in neural networks: An overview (2014, background): “Such NNs learn to perceive/encode/predict/ classify patterns or pattern sequences, but they do not learn to act in the more general sense of Reinforcement Learning (RL) in unknown environments (see surveys, e.g., Kaelbling et al., 1996; Sutton & Barto, 1998; Wiering & van Otterlo, 2012).”
Emergence of multimodal action representations from neural network self-organization (2017, methodology): “…the process of input-driven selforganization exhibited by topographic maps in the cortex (Miikkulainen, Bednar, Choe, & Sirosh, 2005; Nelson, 2000; Willshaw & von der Malsburg, 1976), we proposed a learning model encompassing a hierarchy of Growing When Required (GWR) networks (Marsland et al.,…”
Critical period plasticity in local cortical circuits (2005, background): “In computational models of self-organization, the recipient cortical circuits largely determine the final spacing of column”
Prototype-based Neural Network Layers: Incorporating Vector Quantization (2018, methodology): “The distance based perspective in prototype-based methods offers a clear understanding of the prototype principle and the WTA-rule provides many interpretation techniques e. g. biological excitation in neural maps or local area winner in Heskes-Self-Organizing-Maps [41, 42, 43].”
A Self-Organizing Neural Model of Motor Equivalent Reaching and Tool Use by a Multijoint Arm (1993, background): “These corollary discharges may be combined directly with the vector DV, to form PDM,, via a self-organizing feature map (Grossberg, 1976, 1982; Gross-berg & Kuperstein, 1986,1989; Kohonen, 1988; Malsburg, 1973; Willshaw & Malsburg, 1976).”
Introduction to artificial neural networks. (2007, background): “ANNs are data processing mechanisms that do not follow specific rules to process data, but which use the data they receive to discover the rules governing them [19,20].”
Copying and Evolution of Neuronal Topology (2008, background): “The mechanism of self-replication utilizes known neurophysiological mechanisms; namely, topographic map formation [36,37], STDP [38] and neuronal resetting [39].”