ML: Rnn

Machine-learning ideas tagged Rnn in the ML taxonomy of the Math2NN corpus.

597 ideas found

Unverified 2026

Fold-aware fast-slow neural state layer

Replace a single recurrent or neural-ODE state update by a fast subsystem for the rapidly relaxing state and a slow subsystem for context, memory, or parameters. Constrain the learned algebraic critical manifold to remain normally hyperbolic during ordinary operation, while treating its folds as explicit, detectable transition surfaces that can generate controlled regime changes rather than numerical blow-up.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Constructing far-from-equilibrium patterns in a cross-diffusion vegetation-autotoxicity model arXiv:2607.15692
Unverified 2026

Periodic-block recurrent dynamics

Replace a generic recurrent transition by an exactly periodic unitary base transition plus a learnable weak Hermitian perturbation. The resulting \(\tau\)-step macro-dynamics approximates a continuous-time unitary flow, allowing the model to preserve signal norms while learning slowly varying long-range transformations.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Robustness of periodicity in Grover walks under a magnetic vector potential arXiv:2607.14797
Unverified 2026

Delay-Resonance Monitor for Oscillatory Hidden States

Augment a recurrent or state-space neural network with an explicit delayed hidden-state channel and monitor the linearized delay spectrum around the zero or operating-point state. Use the paper's antiperiodic resonance equations to predict when oscillatory hidden modes should appear, then either avoid those parameter regions for stable sequence prediction or deliberately target them for periodic-memory tasks.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Bifurcations of periodic and antiperiodic orbits near an equilibrium in autonomous differential delay systems with one or two delays arXiv:2607.14533
Unverified 2026

Moment-Resolved Stochastic Reservoir Readout

Replace mean-only readout from a noisy recurrent or Langevin reservoir by concatenating empirical first, second, and fourth raw moments of each hidden coordinate. The second and fourth moments retain input-dependent width and tail information generated by nonlinear confinement, while multiple independently initialized reservoirs can be concatenated before the final linear classifier to preserve complementary features.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Moment-Resolved Readout and Reservoir Diversity in Nonequilibrium Langevin Computing arXiv:2607.14520
Unverified 2026

Sliding-Friction Recurrent Memory

Replace a single recurrent state with two coupled one-dimensional latent chains whose relative alignment is periodically shifted during inference. Ferromagnetic coupling preserves locally coherent patterns, while controlled sliding produces a nonequilibrium friction effect that can make global magnetization substantially longer-lived than in a static noisy chain. The shift velocity acts as a measurable memory-control parameter rather than an unconstrained architectural hyperparameter.

Useful6/10
Difficulty6/10
Novelty8/10
Paper: Long-lived memory in sliding spin chains arXiv:2607.14383
Unverified 2026

Automorphic All-Pass Recurrent Layer

Parameterize a recurrent or state-space layer by a matrix-valued Blaschke lift instead of an unconstrained transition matrix. The resulting causal filter is contractive for inputs inside the unit disk and energy-preserving on the unit circle, while its value at z=0 is a freely learned strict contraction.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Automorphic Nelson Dilations for Contractions and Invariant Subspace Tracking arXiv:2607.14372
Unverified 2026

Threshold-Projection Recurrent Memory

Replace or augment a recurrent cell with multiple hysteresis memory branches whose states remain unchanged while the input stays within a branch-specific radius, then move toward the current input only when that radius is exceeded. The resulting cell has explicit persistence and bounded state changes, giving it an inductive bias for temporal hysteresis and reducing the need for the network to learn long-term memory behavior from scratch.

Useful6/10
Difficulty4/10
Novelty7/10
Paper: Accounting for Hysteresis and Eddy Currents in Finite Element Simulations of Ferromagnetic Laminated Cores using a Recurrent Neural Network arXiv:2607.14321
Unverified 2026

Signature-memory neural CDE

Replace an unconstrained recurrent memory with a truncated path-signature state that is updated continuously from the input control path. Feed this structured state to a learned vector field, allowing the model to represent path-dependent dynamics through iterated integrals of the entire history rather than only the latest hidden state.

Useful6/10
Difficulty5/10
Novelty5/10
Paper: Dynamic Universal Approximation via Signature Controlled Differential Equations arXiv:2607.13886
Unverified 2026

Cρ-stable recurrent transition

Constrain the transition matrix of an RNN or linear state-space model to the paper's class Cρ instead of controlling only its spectral radius or spectral norm. The resulting transition has an explicit dilation certificate and satisfies ∥T^n∥ ≤ ρ for every time horizon, preventing exploding hidden states while retaining nonnormal dynamics that ordinary spectral normalization may remove.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Complete functional calculus bounds for $ρ$-contractions arXiv:2607.13794
Unverified 2026

Margulis-Balanced Expanding Recurrent Layer

Add a regularizer to a recurrent or state-space transition that makes its expansion along a learned one-dimensional direction approximately constant across hidden states. A learned potential can absorb state-dependent terms, implementing the paper's cohomology mechanism rather than forcing the raw Jacobian to be constant.

Useful6/10
Difficulty6/10
Novelty8/10
Paper: Margulis Measures on Expanding Foliations: Construction and Rigidity arXiv:2607.13556
Unverified 2026

SRB Entropy-Lyapunov Regularizer

Add an entropy-Lyapunov consistency term to a recurrent or state-space model whose learned dynamics are intended to reproduce a chaotic invariant distribution. The regularizer targets the equality condition h_mu(f) = sum_i max(lambda_i, 0), while a dominated-splitting diagnostic determines whether the theorem assumptions are approximately plausible instead of blindly forcing equality.

Useful6/10
Difficulty6/10
Novelty8/10
Paper: SRB Measures for $C^{1+\mathrm{Dini}}$ Diffeomorphisms arXiv:2607.13530
Unverified 2026

Finite-Orbit Circulant State Core

Replace the linear state transition in a small recurrent or state-space module by a circulant matrix acting on a vector over a finite field. The hidden state then has only finitely many possible values and follows an exactly periodic orbit after at most \(q^n\) states, eliminating numerical drift on modular-counting and symbolic-memory tasks. A learned real-valued encoder and decoder can surround the discrete core, while the transition itself is fixed, searched, or trained with a…

Useful6/10
Difficulty6/10
Novelty8/10
Paper: Periodicities in the Riordan arrays of polynomials over finite fields arXiv:2607.13442
Unverified 2026

Third-Order Nilpotent Memory Cell

Replace or augment an RNN or state-space model hidden state with coordinates on a bounded 3-step nilpotent group. The first layer stores ordinary features, the second layer stores pairwise commutator memory, and the third layer stores nested commutators that can preserve three-time dependencies invisible to first- and second-order summaries. Layered reduction keeps the state bounded while retaining the algebraic interaction structure.

Useful6/10
Difficulty7/10
Novelty8/10
Paper: Non-vanishing of multiple correlation sequences arXiv:2607.13286
Unverified 2026

Multiplier-Aware Anti-Flip Optimizer

Treat consecutive optimizer updates as a discrete dynamical system and monitor the dominant local multiplier of the parameter-update map. When an estimated real multiplier approaches -1, apply damping or reduce the learning rate, because the paper's mechanism predicts the onset of an alternating period-2 orbit before ordinary divergence is visible.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: A Model of Annual Tick Population Density in the Eastern United States as a Function of Questing Behavior and Host Availability arXiv:2607.13280
Unverified 2026

Saturating Trail Memory for Asynchronous Multi-Agent Networks

Equip multiple recurrent agents with a shared spatial or token-level trail field whose influence is a bounded function of accumulated visitation, rather than an unbounded additive memory. Use the paper's simultaneous/sequential invariance as a falsifiable design target: parallel and randomly ordered asynchronous agent updates should produce nearly identical predictions when trail occupancy is saturated, while deliberately nonsaturating controls should show order dependence. This can enable…

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Exact collective first-passage statistics of N trail-interacting walkers arXiv:2607.13213
Unverified 2026

Subspace-Restarted State-Space Dynamics

Split a recurrent or state-space model into a persistent slow state and a fast internal state. Every r recurrent steps, preserve the slow state but reset or contract the fast state toward a learned reference, reproducing selective restart rather than a destructive global reset. The expected benefit is suppression of long-range oscillatory and error correlations while retaining trajectory-level information.

Useful6/10
Difficulty4/10
Novelty7/10
Paper: Emergence of drifted diffusion in quantum walks with subspace restart arXiv:2607.12727
Unverified 2026

Microcanonical Krylov Stability Monitor

Construct a Lanczos chain for the neural-network vector field or hidden-state evolution, separately within bins of approximately constant loss, energy, or activation norm. Use the resulting Krylov complexity and Lanczos-coefficient growth as an early-warning signal for unstable training or long-horizon hidden-state amplification, then reduce the learning rate or recurrent integration step only in the unstable shells.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: From phase space to Krylov space, one shell at a time arXiv:2607.12585
Unverified 2026

Latent Reference Governor for Safe SSMs

Insert a reference governor between a neural model's raw latent command and a linear state-space update, so that hidden states and outputs remain inside a prescribed union of polytopes. At every step, choose the largest interpolation toward the desired command whose predicted trajectory remains in the offline safe set. This can prevent hidden-state explosions and invalid latent trajectories without globally shrinking the model's weights.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: Dynamically Feasible Planning and Control in Complex Environments: a Scalable Systematic Approach arXiv:2607.12178
Unverified 2026

Norm-aware feedback learning-rate preconditioner

Use the feedbacked control-to-state norm as a conditioning diagnostic to adapt the optimizer step applied to recurrent residual outputs. When the estimated horizon amplification is large, reduce or precondition the residual-control update; when feedback makes it small, permit larger updates.

Useful6/10
Difficulty4/10
Novelty6/10
Paper: Stabilize-then-optimize: Feedback transformations as preconditioners in optimal control arXiv:2607.11835
Unverified 2026

Lorentzian SU(2) recurrent flow

Use the paper's explicitly solved SU(2)-based extremal flow as a structured recurrent transition instead of learning an unconstrained dense recurrent matrix. The transition has only two scalar parameters, a radius/frequency r and phase phi, while its rotating coefficient pattern continuously mixes four real state coordinates and can be integrated with a norm-preserving Cayley transform.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: The Lorentzian Problem on the Group $SU(2)$ arXiv:2607.11592
Unverified 2026

Algebraic-Invariant Residual Layer

Represent a rational-like feature transformation with an auxiliary state y constrained by polynomial equations G(x,y)=0, and update x and y jointly along the tangent space of that constraint manifold. This creates residual blocks in which nonlinear feature identities remain consistent over many layers or time steps, reducing auxiliary-variable drift and potentially stabilizing rational activations and implicit recurrent dynamics.

Useful6/10
Difficulty5/10
Novelty8/10
Paper: Algebraic Invariant Quadratization Schemes for Cahn--Hilliard Equations arXiv:2607.11569
Unverified 2026

Spectrally admissible recurrent state

Represent a recurrent transition using finite Jacobi coefficients with strictly positive off-diagonal entries, and regularize exponential moments of the associated spectral measures. This transfers the Toda lattice's exact phase-space condition into a practical certificate for recurrent dynamics. The exact global-well-posedness theorem applies to the autonomous Toda flow, while the neural-network version is a falsifiable regularization hypothesis for learned recurrent perturbations.

Useful6/10
Difficulty6/10
Novelty8/10
Paper: Global well-posedness of the Toda lattice on an exact spectral phase space arXiv:2607.11491
Unverified 2026

Contractive Misspecification-Regularized State Model

Distill a large or accurate latent transition model into a smaller discrete-state recurrent model while penalizing both its one-step transition mismatch and its lack of contraction. The filtering perturbation bound predicts that reducing the Dobrushin coefficient prevents errors from accumulating over long sequences, while reducing the transition discrepancy lowers the irreducible steady-state error.

Useful6/10
Difficulty4/10
Novelty7/10
Paper: An Operator-Theoretic Analysis of Nonlinear Filtering under Model Misspecification arXiv:2607.11378
Unverified 2026

Critical-Block Stability Sensitivity Ranking

Use multilevel sensitivity of the global interaction margin to identify which neural block, connection, or parameter group is responsible for instability. This provides a targeted alternative to uniformly shrinking the learning rate or regularizing every layer.

Useful6/10
Difficulty5/10
Novelty8/10
Paper: Multiple Vehicles and Traction Network Interaction System Stability Analysis and Oscillation Responsibility Identification arXiv:2607.11243