Statistical mechanics for neural networks with continuous-time dynamics
The authors summarize their current knowledge about the long-time behaviour of networks of graded response neurons with continuous-time dynamics. They demonstrate the workings of their previously developed statistical-mechanical approach to continuous-time dynamics by applying it to networks with va...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
1993
|
| In: |
Journal of physics. A, Mathematical and general
Year: 1993, Volume: 26, Issue: 4, Pages: 831-857 |
| ISSN: | 1361-6447 |
| DOI: | 10.1088/0305-4470/26/4/012 |
| Online Access: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1088/0305-4470/26/4/012 Verlag, lizenzpflichtig, Volltext: https://dx.doi.org/10.1088/0305-4470/26/4/012 
|
| Author Notes: | R. Kuhn, S. Bos |
| Summary: | The authors summarize their current knowledge about the long-time behaviour of networks of graded response neurons with continuous-time dynamics. They demonstrate the workings of their previously developed statistical-mechanical approach to continuous-time dynamics by applying it to networks with various forms of synaptic organization (learning rules), and neural composition (neuron-types as encoded in gain functions), as well as to networks varying with respect to the ensemble of stored data (unbiased and low-activity patterns). They present phase diagrams and compute distributions of local fields for a variety of examples. Local field distributions are found to deviate from the Gaussian form obtained for stochastic neurons in the context of the replica approach. A solution to the low firing rates problems within the framework of nets of analogue neurons is also briefly discussed. Finally, the statistical-mechanical approach to the analysis of continuous-time dynamics is extended to include effects of fast stochastic noise. |
|---|---|
| Item Description: | Falsche Namensform in der Verfasserangabe. Richtig: Kühn, Reimer und Bös, S Gesehen am 15.06.2023 |
| Physical Description: | Online Resource |
| ISSN: | 1361-6447 |
| DOI: | 10.1088/0305-4470/26/4/012 |