Accuracy and capacity of modern Hopfield networks with synaptic noise.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 41116394.
- Also identified by DOI 10.1103/nwbb-n1bc.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
We study the retrieval accuracy and capacity of modern Hopfield networks of with two-state (Ising) spins interacting via modified Hebbian n-spin interactions. In particular, we consider systems where the interactions deviate from the Hebb rule through additive or multiplicative noise or through clipping or deleting interactions. We find that the capacity scales as N^{n-1} with the number of spins N in all cases, but with a prefactor reduced compared to the Hebbian case. For n=2 our results agree with the previously known results for the conventional n=2 Hopfield network.