On setting unit thresholds in an incompletely connected associative net Network: Comput
By J. Buckingham, David J. Willshaw. 1993
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Andreas Knoblauch
- Friedrich T. Sommer
- Edgar Körner
- Günther Palm
- Ursula Körner
- Friedhelm Schwenker
- Holger Bosch
- Franz J. Kurfess
Citations in the corpus
- Structural Synaptic Plasticity Has High Memory Capacity and Can Explain Graded Amnesia, Catastrophic Forgetting, and the Spacing Effect (2014, background): “In fact, an optimal threshold control as presumed above would actually require silent synapses in order to compute spike thresholds Hj~c’(j) in incompletely connected excitatory networks with Peffv1 [143,144] (so they should not be pruned).”
- Memory Capacities for Synaptic and Structural Plasticity (2010, background): “, 1996; Sommer and Palm, 1999), Improved threshold strategies (Buckingham and Willshaw, 1993; Graham and Willshaw, 1995), and retrieval with spiking neurons (Knoblauch and Palm, 2001; Knoblauch, 2003b) can significantly improve network capacity and retrieval accuracy in small memory networks.”
- Improved bidirectional retrieval of sparse patterns stored by Hebbian learning (1999, unknown): “Section 4.3 contains a refined analysis of the finite size Willshaw model: an improved combinatorial calculation of retrieval error probabilities is derived (Proposition 4.2) that allows much faster numerical evaluation than the previously given formula (Buckingham and Willshaw, 1993).”
- Neural Associative Memory with Optimal Bayesian Learning (2011, background): “Exact potential distributions are well known and can be used to compute optimal firing thresholds (Palm, 1980; Buckingham & Willshaw, 1992, 1993; Knoblauch, 2008; Knoblauch et al., 2010).”
- Iterative retrieval of sparsely coded associative memory patterns (1996, background): “Basically,threshold setting in a neural network can be carried out by setting a global threshold = j [Palm, 1980, Gibson and Robinson, 1992], or by setting individual threshold values j [Marr, 1971, Buckingham and Willshaw, 1993].”
- Information storage capacity of incompletely connected associative memories (1998, methodology): “69 for full connectivity, con rming Palm's result of C = log(2).”