Learning Discrete Successor Transitions in Continuous Attractor Networks: Emergence, Limits, and Topological Constraints

• URL: http://arxiv.org/abs/2601.15336v1
• Date: Tue, 20 Jan 2026 10:41:18 GMT
• Title: Learning Discrete Successor Transitions in Continuous Attractor Networks: Emergence, Limits, and Topological Constraints
• Authors: Daniel Brownell,
• Abstract summary: Continuous attractor networks (CANs) represent low-dimensional continuous variables such as head direction, spatial position, and phase.<n>In canonical spatial domains, transitions along the attractor manifold are driven by continuous displacement signals.<n>We present an experimental framework for training CANs to perform successor-like transitions between stable attractor states.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continuous attractor networks (CANs) are a well-established class of models for representing low-dimensional continuous variables such as head direction, spatial position, and phase. In canonical spatial domains, transitions along the attractor manifold are driven by continuous displacement signals, such as angular velocity-provided by sensorimotor systems external to the CAN itself. When such signals are not explicitly provided as dedicated displacement inputs, it remains unclear whether attractor-based circuits can reliably acquire recurrent dynamics that support stable state transitions, or whether alternative predictive strategies dominate. In this work, we present an experimental framework for training CANs to perform successor-like transitions between stable attractor states in the absence of externally provided displacement signals. We compare two recurrent topologies, a circular ring and a folded snake manifold, and systematically vary the temporal regime under which stability is evaluated. We find that, under short evaluation windows, networks consistently converge to impulse-driven associative solutions that achieve high apparent accuracy yet lack persistent attractor dynamics. Only when stability is explicitly enforced over extended free-run periods do genuine attractor-based transition dynamics emerge. This suggests that shortcut solutions are the default outcome of local learning in recurrent networks, while attractor dynamics represent a constrained regime rather than a generic result. Furthermore, we demonstrate that topology strictly limits the capacity for learned transitions. While the continuous ring topology achieves perfect stability over long horizons, the folded snake topology hits a geometric limit characterized by failure at manifold discontinuities, which neither curriculum learning nor basal ganglia-inspired gating can fully overcome.

Related papers

• When Sensors Fail: Temporal Sequence Models for Robust PPO under Sensor Drift [64.37959940809633]
  We study robustness of Proximal Policy Optimization (PPO) under temporally persistent sensor failures.<n>We show Transformer-based sequence policies substantially outperform, RNN, and SSMs in robustness, maintaining high returns even when large fractions of sensors are unavailable.
  arXiv  Detail & Related papers  (2026-03-04T22:21:54Z)
• KoopGen: Koopman Generator Networks for Representing and Predicting Dynamical Systems with Continuous Spectra [65.11254608352982]
  We introduce a generator-based neural Koopman framework that models dynamics through a structured, state-dependent representation of Koopman generators.<n>By exploiting the intrinsic Cartesian decomposition into skew-adjoint and self-adjoint components, KoopGen separates conservative transport from irreversible dissipation.
  arXiv  Detail & Related papers  (2026-02-15T06:32:23Z)
• Controlling Dissipative Topology Through Floquet Driving: From Transient Diagnostics to Boundary States Isolation [0.0]
  We show how periodic driving serves as a powerful handle to manipulate dissipative topological phases and dynamically isolate the boundary modes.<n>Our results provide convincing evidence that periodic driving serves as a powerful handle to manipulate dissipative topological phases and dynamically isolate the boundary modes.
  arXiv  Detail & Related papers  (2025-11-28T14:38:22Z)
• Manifestations of flow topology in a quantum driven-dissipative system [0.0]
  In driven-dissipative bosonic systems, the interplay between coherent driving, inter-particle interactions and dissipation leads to a rich variety of non-equilibrium stationary states (NESS)<n>In the semiclassical limit, the flow topology of phase-space dynamics governs the stability and structure of these dynamical phases.
  arXiv  Detail & Related papers  (2025-08-22T16:01:41Z)
• Forecasting Continuous Non-Conservative Dynamical Systems in SO(3) [51.510040541600176]
  We propose a novel approach to modeling the rotation of moving objects in computer vision.<n>Our approach is agnostic to energy and momentum conservation while being robust to input noise.<n>By learning to approximate object dynamics from noisy states during training, our model attains robust extrapolation capabilities in simulation and various real-world settings.
  arXiv  Detail & Related papers  (2025-08-11T09:03:10Z)
• Generative System Dynamics in Recurrent Neural Networks [56.958984970518564]
  We investigate the continuous time dynamics of Recurrent Neural Networks (RNNs)<n>We show that skew-symmetric weight matrices are fundamental to enable stable limit cycles in both linear and nonlinear configurations.<n> Numerical simulations showcase how nonlinear activation functions not only maintain limit cycles, but also enhance the numerical stability of the system integration process.
  arXiv  Detail & Related papers  (2025-04-16T10:39:43Z)
• Nonlinearity-driven Topology via Spontaneous Symmetry Breaking [79.16635054977068]
  We consider a chain of parametrically-driven quantum resonators coupled only via weak nearest-neighbour cross-Kerr interaction.<n>Topology is dictated by the structure of the Kerr nonlinearity, yielding a non-trivial bulk-boundary correspondence.
  arXiv  Detail & Related papers  (2025-03-15T00:20:45Z)
• Back to the Continuous Attractor [4.866486451835401]
  Continuous attractors offer a unique class of solutions for storing continuous-valued variables in recurrent system states for indefinitely long time intervals.<n>Unfortunately, continuous attractors suffer from severe structural instability in general--they are destroyed by most infinitesimal changes of the dynamical law that defines them.<n>We observe that the bifurcations from continuous attractors in theoretical neuroscience models display various structurally stable forms.<n>We build on the persistent manifold theory to explain the commonalities between bifurcations from and approximations of continuous attractors.
  arXiv  Detail & Related papers  (2024-07-31T18:37:05Z)
• Topological, multi-mode amplification induced by non-reciprocal, long-range dissipative couplings [39.58172554437255]
  We show the emergence of unconventional, non-reciprocal, long-range dissipative couplings induced by the interaction of the bosonic chain with a chiral, multimode channel.<n>We also show how these couplings can also display topological amplifying phases that are dynamically stable in the presence of local parametric drivings.
  arXiv  Detail & Related papers  (2024-05-16T15:16:33Z)
• Defining stable phases of open quantum systems [0.0]
  We show that uniformity is satisfied in a canonical classical cellular automaton. We conjecture some sufficient conditions for a channel to exhibit uniformity and therefore stability.
  arXiv  Detail & Related papers  (2023-08-28T17:55:31Z)
• Beyond the Edge of Stability via Two-step Gradient Updates [49.03389279816152]
  Gradient Descent (GD) is a powerful workhorse of modern machine learning. GD's ability to find local minimisers is only guaranteed for losses with Lipschitz gradients. This work focuses on simple, yet representative, learning problems via analysis of two-step gradient updates.
  arXiv  Detail & Related papers  (2022-06-08T21:32:50Z)
• Exceptional Dynamical Quantum Phase Transitions in Periodically Driven Systems [0.0]
  We show that spontaneous symmetry breaking can occur at a short-time regime. Our results open up research for hitherto unknown phases in short-time regimes.
  arXiv  Detail & Related papers  (2020-12-22T04:04:56Z)
• Self-consistent theory of mobility edges in quasiperiodic chains [62.997667081978825]
  We introduce a self-consistent theory of mobility edges in nearest-neighbour tight-binding chains with quasiperiodic potentials. mobility edges are generic in quasiperiodic systems which lack the energy-independent self-duality of the commonly studied Aubry-Andr'e-Harper model.
  arXiv  Detail & Related papers  (2020-12-02T19:00:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.