Neural Associative Memory and the Willshaw--Palm Probability Distribution

25 citations recorded by the source corpus.

How researchers see this paper

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

Structural Synaptic Plasticity Has High Memory Capacity and Can Explain Graded Amnesia, Catastrophic Forgetting, and the Spacing Effect (2014, background): “22 in [129] we obtain pPh for the special case of fully connected networks (P~1),”
Zip nets: Efficient associative computation with binary synapses (2010, unknown): “(7)”
Neural Associative Memory with Optimal Bayesian Learning (2011, methodology): “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).”
Memory Capacities for Synaptic and Structural Plasticity (2010, unknown): “Knoblauch ( 2007 , 2008 ) shows that equation 3.”
Optimal synaptic learning in non-linear associative memory (2010, background): “…in similar network models by structural plasticity (meaning the elimination and generation of synapses [60]) yields a much higher diverging synaptic capacity where the information that a binary synapse can store scales with the logarithm of the network size n [61], [62], [63], [64], [29], [65].”
Efficient Associative Computation with Discrete Synapses (2016, methodology): “For example, compressed implementations of Willshaw networks can store up to CI = 1 bit per computer bit for almost any nonlogarithmic sparse activity with p → 0 and p ∼ log n/n (Knoblauch, 2008).”