Leakage and Second-Order Dynamics Improve Hippocampal RNN Replay

• URL: http://arxiv.org/abs/2602.18401v1
• Date: Fri, 20 Feb 2026 18:07:09 GMT
• Title: Leakage and Second-Order Dynamics Improve Hippocampal RNN Replay
• Abstract summary: Biological neural networks can generate "replay" resembling stimulus-driven activity.<n>Recent computational models of replay use noisy recurrent neural networks (RNNs) trained to path-integrate.<n>We re-examine noisy RNN replay as sampling to understand or improve it in three ways.
• Score: 18.57036786110829
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Biological neural networks (like the hippocampus) can internally generate "replay" resembling stimulus-driven activity. Recent computational models of replay use noisy recurrent neural networks (RNNs) trained to path-integrate. Replay in these networks has been described as Langevin sampling, but new modifiers of noisy RNN replay have surpassed this description. We re-examine noisy RNN replay as sampling to understand or improve it in three ways: (1) Under simple assumptions, we prove that the gradients replay activity should follow are time-varying and difficult to estimate, but readily motivate the use of hidden state leakage in RNNs for replay. (2) We confirm that hidden state adaptation (negative feedback) encourages exploration in replay, but show that it incurs non-Markov sampling that also slows replay. (3) We propose the first model of temporally compressed replay in noisy path-integrating RNNs through hidden state momentum, connect it to underdamped Langevin sampling, and show that, together with adaptation, it counters slowness while maintaining exploration. We verify our findings via path-integration of 2D triangular and T-maze paths and of high-dimensional paths of synthetic rat place cell activity.

Related papers

• LAPS: Improving Incremental LiDAR Mapping using Active Pooling and Sampling for Neural Distance Fields [11.70788501966735]
  LAPS is a replay management framework for incremental neural mapping.<n>It improves replay retention and replay allocation during online updates.<n>It consistently improves reconstruction completeness while maintaining competitive geometric accuracy.
  arXiv  Detail & Related papers  (2026-05-15T00:22:31Z)
• When Does Non-Uniform Replay Matter in Reinforcement Learning? [43.83763359517116]
  We show that the effectiveness of non-uniform replay is governed by three factors: replay volume, the number of replayed transitions per environment step; expected recency, how recent sampled transitions are; and the entropy of the replay sampling distribution.<n>We adopt a simple Truncated Geometric replay that biases sampling toward recent experience while preserving high entropy and incurring negligible computational overhead.
  arXiv  Detail & Related papers  (2026-05-11T09:11:05Z)
• Stable Video Infinity: Infinite-Length Video Generation with Error Recycling [76.91310169118408]
  We propose Stable Video Infinity (SVI) that is able to generate infinite-length videos with high temporal consistency, plausible scene transitions, and controllable streaming storylines.<n> SVI incorporates Error-Recycling Fine-Tuning, a new type of efficient training that recycles the Diffusion Transformer's self-generated errors into supervisory prompts.<n>We evaluate SVI on three benchmarks, including consistent, creative, and conditional settings, thoroughly verifying its versatility and state-of-the-art role.
  arXiv  Detail & Related papers  (2025-10-10T09:45:46Z)
• Replay Can Provably Increase Forgetting [24.538643224479515]
  A critical challenge for continual learning is forgetting, where the performance on previously learned tasks decreases as new tasks are introduced.<n>One of the commonly used techniques to mitigate forgetting, sample replay, has been shown empirically to reduce forgetting.<n>We show that even in a noiseless setting, forgetting can be non-monotonic with respect to the number of replay samples.
  arXiv  Detail & Related papers  (2025-06-04T18:46:23Z)
• Violence detection in videos using deep recurrent and convolutional neural networks [0.0]
  We propose a deep learning architecture for violence detection which combines both recurrent neural networks (RNNs) and 2-dimensional convolutional neural networks (2D CNN) In addition to video frames, we use optical flow computed using the captured sequences. The proposed approaches reach the same level as the state-of-the-art techniques and sometime surpass them.
  arXiv  Detail & Related papers  (2024-09-11T19:21:51Z)
• Planning in a recurrent neural network that plays Sokoban [6.059513516334741]
  We analyze a recurrent neural network (RNN) trained on Sokoban, a puzzle requiring sequential, irreversible decisions.<n>We find that the RNN has a causal plan representation which predicts its future actions about 50 steps in advance.<n>We extend the trained RNN to significantly larger, out-of-distribution Sokoban puzzles, demonstrating robust representations beyond the training regime.
  arXiv  Detail & Related papers  (2024-07-22T06:57:34Z)
• RoHM: Robust Human Motion Reconstruction via Diffusion [58.63706638272891]
  RoHM is an approach for robust 3D human motion reconstruction from monocular RGB(-D) videos. It conditioned on noisy and occluded input data, reconstructs complete, plausible motions in consistent global coordinates. Our method outperforms state-of-the-art approaches qualitatively and quantitatively, while being faster at test time.
  arXiv  Detail & Related papers  (2024-01-16T18:57:50Z)
• Curious Replay for Model-based Adaptation [3.9981390090442686]
  We present Curious Replay, a form of prioritized experience replay tailored to model-based agents. Agents using Curious Replay exhibit improved performance in an exploration paradigm inspired by animal behavior. DreamerV3 with Curious Replay surpasses state-of-the-art performance on the Crafter benchmark.
  arXiv  Detail & Related papers  (2023-06-28T05:34:53Z)
• Backdoor Defense via Suppressing Model Shortcuts [91.30995749139012]
  In this paper, we explore the backdoor mechanism from the angle of the model structure. We demonstrate that the attack success rate (ASR) decreases significantly when reducing the outputs of some key skip connections.
  arXiv  Detail & Related papers  (2022-11-02T15:39:19Z)
• Minkowski Tracker: A Sparse Spatio-Temporal R-CNN for Joint Object Detection and Tracking [53.64390261936975]
  We present Minkowski Tracker, a sparse-temporal R-CNN that jointly solves object detection and tracking problems. Inspired by region-based CNN (R-CNN), we propose to track motion as a second stage of the object detector R-CNN. We show in large-scale experiments that the overall performance gain of our method is due to four factors.
  arXiv  Detail & Related papers  (2022-08-22T04:47:40Z)
• Progressive Latent Replay for efficient Generative Rehearsal [9.267156820352996]
  We introduce a new method for internal replay that modulates the frequency of rehearsal based on the depth of the network. We name our method Progressive Latent Replay and show that it outperforms Internal Replay while using significantly fewer resources.
  arXiv  Detail & Related papers  (2022-07-04T16:28:05Z)
• Replay in Deep Learning: Current Approaches and Missing Biological Elements [33.20770284464084]
  Replay is the reactivation of one or more neural patterns. It is thought to play a critical role in memory formation, retrieval, and consolidation. We provide the first comprehensive comparison between replay in the mammalian brain and replay in artificial neural networks.
  arXiv  Detail & Related papers  (2021-04-01T15:19:08Z)
• Neuroevolution of a Recurrent Neural Network for Spatial and Working Memory in a Simulated Robotic Environment [57.91534223695695]
  We evolved weights in a biologically plausible recurrent neural network (RNN) using an evolutionary algorithm to replicate the behavior and neural activity observed in rats. Our method demonstrates how the dynamic activity in evolved RNNs can capture interesting and complex cognitive behavior.
  arXiv  Detail & Related papers  (2021-02-25T02:13:52Z)
• Cascaded Regression Tracking: Towards Online Hard Distractor Discrimination [202.2562153608092]
  We propose a cascaded regression tracker with two sequential stages. In the first stage, we filter out abundant easily-identified negative candidates. In the second stage, a discrete sampling based ridge regression is designed to double-check the remaining ambiguous hard samples.
  arXiv  Detail & Related papers  (2020-06-18T07:48:01Z)

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.