Improved bidirectional retrieval of sparse patterns stored by Hebbian learning

By Friedrich T. Sommer, Günther Palm. 1999

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

Structural Synaptic Plasticity Has High Memory Capacity and Can Explain Graded Amnesia, Catastrophic Forgetting, and the Spacing Effect (2014, background): “As such models are computationally very demanding, in particular, when simulating longer time intervals in the range of months to years, it is more favorable to use simple iterative extensions of one-step retrieval [27,63,66,67]) that can still mimic many relevant properties of the realistic models.”
Zip nets: Efficient associative computation with binary synapses (2010, background): “Similarly, µhi = E(xj |v µ j = 1) and σ2hi := Var(xj |v µ j = 1) are expectation and variance of the dendritic potential for a high-neuron with vµj = 1.”
Memory Capacities for Synaptic and Structural Plasticity (2010, methodology): “Various studies have shown, however, that modifications of the Willshaw model can overcome this problem: Iterative and bidirectional retrieval schemes (Schwenker et al., 1996; Sommer and Palm, 1999), Improved threshold strategies (Buckingham and Willshaw, 1993; Graham and Willshaw, 1995), and retrie”
Scene segmentation by spike synchronization in reciprocally connected visual areas. II. Global assemblies and synchronization on larger space and time scales (2002, background): “Initially, however, fast oscillatory or fluctuating activity plays an important role in segregating the different assemblies iteratively within about 10 ms in the associative memory (see Schwenker et al. 1996; Sommer and Palm 1998, 1999; Knoblauch and Palm 2001a) to find a proper subassembly withi”
Optimal synaptic learning in non-linear associative memory (2010, background): “…learning models of the Hopfield type [30], [58], [32], [33], [53], [34], [35], [36], [37], simple non-linear learning models of the Willshaw type [24], [23], [25], [59], [26], [28], [18], [29], and BCPNN-type models employing suboptimal Bayesian heuristics [38], [39], [40], [41], [42], [43], [6].”
Neural Associative Memory with Optimal Bayesian Learning (2011, unknown): “…model is the so-called Steinbuch or Willshaw model with binary synapses and clipped Hebbian learning (Willshaw, Buneman, & Longuet-Higgins, 1969; Steinbuch, 1961; Palm, 1980, 1991; Golomb, Rubin, & Sompolinsky, 1990; Nadal, 1991; Sommer & Dayan, 1998; Sommer & Palm, 1999; Knoblauch et al., 2010).”
Synchronization and pattern separation in spiking associative memories and visual cortical areas (2004, methodology): “Finally the validity of the classical binomial approximation of the Willshaw model is discussed using a refined analysis technique [29, 171].”