Drift-Diffusion Matching: Embedding dynamics in latent manifolds of asymmetric neural networks
This work extends attractor neural network theory beyond equilibrium, potentially impacting models of associative and sequential memory in neuroscience and machine learning, though it appears incremental in building on existing RNN and dynamical systems concepts.
The authors tackled the limitation of symmetric connectivity in recurrent neural networks (RNNs) by introducing a framework called drift-diffusion matching to embed arbitrary stochastic dynamical systems in low-dimensional latent subspaces, enabling faithful representation of nonlinear and nonequilibrium dynamics like chaotic attractors.
Recurrent neural networks (RNNs) provide a theoretical framework for understanding computation in biological neural circuits, yet classical results, such as Hopfield's model of associative memory, rely on symmetric connectivity that restricts network dynamics to gradient-like flows. In contrast, biological networks support rich time-dependent behaviour facilitated by their asymmetry. Here we introduce a general framework, which we term drift-diffusion matching, for training continuous-time RNNs to represent arbitrary stochastic dynamical systems within a low-dimensional latent subspace. Allowing asymmetric connectivity, we show that RNNs can faithfully embed the drift and diffusion of a given stochastic differential equation, including nonlinear and nonequilibrium dynamics such as chaotic attractors. As an application, we construct RNN realisations of stochastic systems that transiently explore various attractors through both input-driven switching and autonomous transitions driven by nonequilibrium currents, which we interpret as models of associative and sequential (episodic) memory. To elucidate how these dynamics are encoded in the network, we introduce decompositions of the RNN based on its asymmetric connectivity and its time-irreversibility. Our results extend attractor neural network theory beyond equilibrium, showing that asymmetric neural populations can implement a broad class of dynamical computations within low-dimensional manifolds, unifying ideas from associative memory, nonequilibrium statistical mechanics, and neural computation.