Pattern Storage, Bifurcations and Higher-Order Correlation Structure of an Exactly Solvable Asymmetric Neural Network Model
Exactly solvable neural network models with asymmetric weights are rare, and exact solutions are available only in some mean-field approaches. In this article we find exact analytical solutions of an asymmetric spin-glass-like model of arbitrary size and we perform a complete study of its dynamical and statistical properties. The network has discrete-time evolution equations, binary firing rates and can be driven by noise with any distribution. We find analytical expressions of the conditional and stationary joint probability distributions of the membrane potentials and the firing rates. The conditional probability distribution of the firing rates allows us to introduce a new learning rule to store safely, under the presence of noise, point and cyclic attractors, with important applications in the field of content-addressable memories. Furthermore, we study the neuronal dynamics in terms of the bifurcation structure of the network. We derive analytically examples of the codimension one and codimension two bifurcation diagrams of the network, which describe how the neuronal dynamics changes with the external stimuli. In particular, we find that the network may undergo transitions among multistable regimes, oscillatory behavior elicited by asymmetric synaptic connections, and various forms of spontaneous symmetry-breaking. On the other hand, the joint probability distributions allow us to calculate analytically the higher-order correlation structure of the network, which reveals neuronal regimes where, statistically, the membrane potentials and the firing rates are either synchronous or asynchronous. Our results are valid for networks composed of an arbitrary number of neurons, but for completeness we also derive the network equations in the mean-field limit and we study analytically their local bifurcations. All the analytical results are extensively validated by numerical simulations.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
On associative neural networks for sparse patterns with huge capacities
Generalized Hopfield models with higher-order or exponential interaction terms are known to have substantially larger storage capacities than the classical quadratic model. On the other hand, associative memories for spa…
Effects of Feature Correlations on Associative Memory Capacity
We investigate how feature correlations influence the capacity of Dense Associative Memory (DAM), a Transformer attention-like model. Practical machine learning scenarios involve feature-correlated data and learn represe…
Reconstructing Gridded Data from Higher Autocorrelations
The higher-order autocorrelations of integer-valued or rational-valued gridded data sets appear naturally in X-ray crystallography, and have applications in computer vision systems, correlation tomography, correlation sp…
Using deep learning for an automatic detection and classification of the vascular bifurcations along the Circle of Willis
Most of the intracranial aneurysms (ICA) occur on a specific portion of the cerebral vascular tree named the Circle of Willis (CoW). More particularly, they mainly arise onto fifteen of the major arterial bifurcations co…
Medical Image AnalysisMathematical studies of the dynamics of finite-size binary neural networks: A review of recent progress
Traditional mathematical approaches to studying analytically the dynamics of neural networks rely on the mean-field approximation, which is rigorously applicable only to networks of infinite size. However, all existing r…