
Maoz Shamir
Senior Academic
Thouless-Anderson-Palmer equations for neural networks
Previous derivation of the Thouless-Anderson-Palmer (TAP) equations for the Hopfield model by the cavity method yielded results that were inconsistent with those of the perturbation theory as well as the results derived by the replica theory of the model. Here we present a derivation of the TAP equation for the Hopfield model by the cavity method and show that it agrees with the form derived by perturbation theory. We also use the cavity method to derive TAP equations for the pseudoinverse neural network model. These equations are consistent with the results of the replica theory of these models.
| Publication language | English |
| Pages | 1839-1844 |
| Journal | Physical Review E |
| Volume | 61 |
| Issue number | 2 |
| Publication status | Published - 01.01.2000 |
ASJC Scopus subject areas
Statistical and Nonlinear Physics
Statistics and Probability
Condensed Matter Physics