Loading...
Please wait, while we are loading the content...
Similar Documents
Retrieval dynamics of neural networks for sparsely coded sequential patterns (1998)
| Content Provider | CiteSeerX |
|---|---|
| Author | Kitano, Katsunori Aoyagi, Toshio |
| Abstract | It is well known that a sparsely coded network in which the activity level is extremely low has intriguing equilibrium properties. In the present work, we study the dynamical properties of a neural network designed to store sparsely coded sequential patterns rather than static ones. Applying the theory of statistical neurodynamics, we derive the dynamical equations governing the retrieval process which are described by some macroscopic order parameters such as the overlap. It is found that our theory provides good predictions for the storage capacity and the basin of attraction obtained through numerical simulations. The results indicate that the nature of the basin of attraction depends on the methods of activity control employed. Furthermore, it is found that robustness against random synaptic dilution slightly deteriorates with the degree of sparseness. For the purpose of constructing more realistic mathematical neural network models (e.g, the Hopfield model [1]), so-called “random ” patterns, which have been used for simple theoretical treatments, have been reconsidered. In a network capable of processing |
| File Format | |
| Journal | Journal of Physics A: Mathematical and General |
| Language | English |
| Publisher Date | 1998-01-01 |
| Access Restriction | Open |
| Subject Keyword | Neural Network Retrieval Dynamic Sequential Pattern Simple Theoretical Treatment Retrieval Process Present Work Realistic Mathematical Neural Network Model Dynamical Equation Activity Level Good Prediction Storage Capacity Hopfield Model So-called Random Pattern Coded Sequential Pattern Coded Network Numerical Simulation Dynamical Property Equilibrium Property Macroscopic Order Parameter Statistical Neurodynamics Activity Control Static One Random Synaptic Dilution |
| Content Type | Text |
| Resource Type | Article |
