Development of feature detectors by self-organization. A network model.

How researchers see this paper

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

Deep learning in neural networks: An overview (2014, background): “Many papers of the previous millennium, however, were about unsupervised learning (UL) without a teacher (e.g., Hebb, 1949; von der Malsburg, 1973; Kohonen, 1972, 1982, 1988; Willshaw and von der Malsburg, 1976; Grossberg, 1976a,b; Watanabe, 1985; Rumelhart and Zipser, 1986; Pearlmutter and Hinton, ”
Learning Factorial Codes by Predictability Minimization (1992, methodology): “Existing “neural” methods for decreasing output redundancy (e.g., Linsker 1988; Zemel and Hinton 1991; Oja 1989; Sanger 1989; Foldikk 1990; Rubner and Schulten 1990; Silva and Almeida 1991) are mostly restricted to the linear case and do not aim at the ambitious general goal of statistical…”
Information processing, dimensionality reduction and reinforcement learning in the basal ganglia. (2003, methodology): “The model devised by Kung and Diamantaras (and an earlier model (Rubner and Tavan, 1989; Rubner and Schulten, 1990)) uses hierarchical lateral connectivity between the output layer neurons (Kung and Diamantaras, 1990; Diamantaras and Kung, 1996) in which neuron i is connected to neurons i + 1 throug”
Semilinear Predictability Minimization Produces Well-Known Feature Detectors (1996, methodology): “See Figure 8 for an example.4 DISCUSSIONWe do not claim that PM is the only parallel method (as opposed to sequential methods, e.g.Rubner and Schulten, 1990) that can lead to well-known feature detectors.”