Abstract
A stochastic physical model is proposed for a certain class of neurocomputational architectures. The present study is based on considering the potentials of each neuron as a fluctuating quantity. In describing this process, a fluctuation can be understood, in a thermodynamic framework, if one considers the behavior of the variables (the neural potentials in this model) in a system with different types of interaction with the rest of the universe. If this interaction is measured by a temperature T (with the system submerged in a thermic bath), by making T → 0 one obtains an equilibrium system where the dynamic variables do not change through time. Since a macroscopic configuration corresponds to many microscopic states, the variables involved are not completely stationary, and they vary near the equilibrium state; any fluctuation will tend to that state. If one considers the dynamic variables as fluctuations of a subsystem (a neuron) from a closed system (a neural network), one obtains an important physical model since it contains many of the existing phenomena of relaxation in many fields of statistical mechanics.
Original language | English |
---|---|
Pages | 573-576 |
Number of pages | 4 |
DOIs | |
State | Published - 1990 |
Externally published | Yes |
Event | 1990 International Joint Conference on Neural Networks - IJCNN 90 Part 3 (of 3) - San Diego, CA, USA Duration: 17 Jun 1990 → 21 Jun 1990 |
Conference
Conference | 1990 International Joint Conference on Neural Networks - IJCNN 90 Part 3 (of 3) |
---|---|
City | San Diego, CA, USA |
Period | 17/06/90 → 21/06/90 |