SciPost Physics Lecture Notes · 2024 · 11 citations · 32 references
Natural SciencesPhysicsComplex SystemsComputational PhysicsDynamical SystemsDissipative SystemsNetwork DynamicsNeural Circuit DynamicsNeural NetworksNeuronal DynamicsSynaptic ConnectivityDynamical Mean-field TheoryFluctuation-dissipation TheoremMean-field DynamicsMean-field TheoryNeural DynamicsNeural Network DynamicsNeuronal Network DynamicsNumerical Modeling
Dynamical mean-field theory is a powerful physics tool used to analyze the typical behavior of neural networks, where neurons can be recurrently connected, or multiple layers of neurons can be stacked. However, it is not easy for beginners to access the essence of this tool and the underlying physics. Here, we give a pedagogical introduction of this method in a particular example of random neural networks, where neurons are randomly and fully connected by correlated synapses and therefore the network exhibits rich emergent collective dynamics. We also review related past and recent important works applying this tool. In addition, a physically transparent and alternative method, namely the dynamical cavity method, is also introduced to derive exactly the same results. The numerical implementation of solving the integro-differential mean-field equations is also detailed, with an illustration of exploring the fluctuation dissipation theorem.
32
Fluctuations and Irreversible Processes
Lars Onsager, Stefan Machlup · Physical Review · 1953 · 1.8K citations
Chaos in Random Neural Networks
Haim Sompolinsky, A. Crisanti, H.-J. Sommers · Physical Review Letters · 1988 · 1.1K citations