Correlated attractors from uncorrelated stimuli
Neural Computation
John Von Neumann and Norbert Wiener: From Mathematics to the Technologies of Life and Death
John Von Neumann and Norbert Wiener: From Mathematics to the Technologies of Life and Death
Theory of Neural Information Processing Systems
Theory of Neural Information Processing Systems
On the equivalence of Hopfield networks and Boltzmann Machines
Neural Networks
Multitasking attractor networks with neuronal threshold noise
Neural Networks
Hi-index | 0.00 |
In this work, we first revise some extensions of the standard Hopfield model in the low storage limit, namely the correlated attractor case and the multitasking case recently introduced by the authors. The former case is based on a modification of the Hebbian prescription, which induces a coupling between consecutive patterns and this effect is tuned by a parameter a. In the latter case, dilution is introduced in pattern entries, in such a way that a fraction d of them is blank. Then, we merge these two extensions to obtain a system able to retrieve several patterns in parallel and the quality of retrieval, encoded by the set of Mattis magnetizations {m^@m}, is reminiscent of the correlation among patterns. By tuning the parameters d and a, qualitatively different outputs emerge, ranging from highly hierarchical to symmetric. The investigations are accomplished by means of both numerical simulations and statistical mechanics analysis, properly adapting a novel technique originally developed for spin glasses, i.e. the Hamilton-Jacobi interpolation, with excellent agreement. Finally, we show the thermodynamical equivalence of this associative network with a (restricted) Boltzmann machine and study its stochastic dynamics to obtain even a dynamical picture, perfectly consistent with the static scenario earlier discussed.