Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks

• URL: http://arxiv.org/abs/2412.15983v1
• Date: Fri, 20 Dec 2024 15:24:28 GMT
• Title: Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks
• Abstract summary: Recurrent Neural Networks (RNNs) are widely used for sequential processing but face limitations with continual inference due to state saturation.<n>We propose an adaptive loss function that eliminates the need for resets during inference while preserving high accuracy over extended sequences.
• Score: 2.1838661321884443
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recurrent Neural Networks (RNNs) are widely used for sequential processing but face fundamental limitations with continual inference due to state saturation, requiring disruptive hidden state resets. However, reset-based methods impose synchronization requirements with input boundaries and increase computational costs at inference. To address this, we propose an adaptive loss function that eliminates the need for resets during inference while preserving high accuracy over extended sequences. By combining cross-entropy and Kullback-Leibler divergence, the loss dynamically modulates the gradient based on input informativeness, allowing the network to differentiate meaningful data from noise and maintain stable representations over time. Experimental results demonstrate that our reset-free approach outperforms traditional reset-based methods when applied to a variety of RNNs, particularly in continual tasks, enhancing both the theoretical and practical capabilities of RNNs for streaming applications.

Related papers

• Frequency Domain Reservoir Computing [10.316233181797408]
  Echo State Networks (ESNs) offer a compelling approach by utilizing fixed recurrent weights to circumvent backpropagation through time.<n>We introduce Frequency Domain Reservoir Computing (FRESCO), an ESN architecture operating entirely in the frequency domain.<n> FRESCO drastically reduces computational costs and energy consumption of training and inference.
  arXiv  Detail & Related papers  (2026-06-23T10:14:46Z)
• Adaptive Recurrent Message Passing for Test Time Computing on Graphs [80.56829418752513]
  We show that recurrent graph models can overcome the intrinsic mismatch between graph data and architectural designs.<n>We propose AdaR, an Adaptive Recurrent graph model, empowering flexible test-time computing on various downstream tasks without changing model parameters.
  arXiv  Detail & Related papers  (2026-06-21T12:14:11Z)
• Robustness Verification of Recurrent Neural Networks with Abstraction Refinement [0.0]
  We propose an abstraction-refinement framework for RNN verification that partitions such intervals to remove the dominant relaxation error.<n>Experiments on CIFAR10 and MNIST stroke benchmarks demonstrate consistent improvements in verification success and robustness-margin tightness over abstraction-only baselines.
  arXiv  Detail & Related papers  (2026-06-10T11:30:37Z)
• Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications [1.226598527858578]
  Bistable Memory Recurrent Unit (BMRU) was introduced to enable hardware-software co-design of ultra-low power RNNs.<n>BMRU performance lags behind parallelizable RNNs on complex sequential tasks.<n>We propose a cumulative update formulation that restores flow while preserving persistent memory, creating skip-connections through time.
  arXiv  Detail & Related papers  (2026-05-12T09:39:33Z)
• When Learning Hurts: Fixed-Pole RNN for Real-Time Online Training [58.25341036646294]
  We analytically examine why learning recurrent poles does not provide tangible benefits in data and empirically offer real-time learning scenarios.<n>We show that fixed-pole networks achieve superior performance with lower training complexity, making them more suitable for online real-time tasks.
  arXiv  Detail & Related papers  (2026-02-25T00:15:13Z)
• ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling [57.91760520589592]
  Scaling network depth has been a central driver behind the success of modern foundation models.<n>This paper revisits the default mechanism for deepening neural networks, namely residual connections.<n>We introduce adaptive neural connection reassignment (ANCRe), a principled and lightweight framework that parameterizes and learns residual connectivities from the data.
  arXiv  Detail & Related papers  (2026-02-09T18:54:18Z)
• Reactive Knowledge Representation and Asynchronous Reasoning [35.58961985804191]
  Exact inference in complex probabilistic models often incurs prohibitive computational costs.<n>Existing methods are often inefficient for ongoing reasoning, as they re-evaluate the entire model upon any change.<n>We first introduce Resin, a probabilistic programming language that merges probabilistic logic with reactive programming.<n>To provide efficient and exact semantics for Resin, we propose Reactive Circuits (RCs)<n>In high-fidelity drone swarm simulations, our approach achieves several orders of magnitude of speedup over frequency-agnostic inference.
  arXiv  Detail & Related papers  (2026-02-05T13:02:01Z)
• Fast Training of Recurrent Neural Networks with Stationary State Feedbacks [48.22082789438538]
  Recurrent neural networks (RNNs) have recently demonstrated strong performance and faster inference than Transformers. We propose a novel method that replaces BPTT with a fixed gradient feedback mechanism.
  arXiv  Detail & Related papers  (2025-03-29T14:45:52Z)
• Lattice-Based Pruning in Recurrent Neural Networks via Poset Modeling [0.0]
  Recurrent neural networks (RNNs) are central to sequence modeling tasks, yet their high computational complexity poses challenges for scalability and real-time deployment. We introduce a novel framework that models RNNs as partially ordered sets (posets) and constructs corresponding dependency lattices. By identifying meet irreducible neurons, our lattice-based pruning algorithm selectively retains critical connections while eliminating redundant ones.
  arXiv  Detail & Related papers  (2025-02-23T10:11:38Z)
• Incremental Online Learning of Randomized Neural Network with Forward Regularization [8.624268246962457]
  We propose a novel Incremental Online Learning process of Randomized Neural Networks (Randomized NN)<n>Within the framework, we further introduce IOL with ridge regularization (-R) and IOL with forward regularization (-F)
  arXiv  Detail & Related papers  (2024-12-17T17:06:33Z)
• Overcoming the Spectral Bias of Neural Value Approximation [17.546011419043644]
  Value approximation using deep neural networks is often the primary module that provides learning signals to the rest of the algorithm. Recent works in neural kernel regression suggest the presence of a spectral bias, where fitting high-frequency components of the value function requires exponentially more gradient update steps than the low-frequency ones. We re-examine off-policy reinforcement learning through the lens of kernel regression and propose to overcome such bias via a composite neural kernel.
  arXiv  Detail & Related papers  (2022-06-09T17:59:57Z)
• Deep Explicit Duration Switching Models for Time Series [84.33678003781908]
  We propose a flexible model that is capable of identifying both state- and time-dependent switching dynamics. State-dependent switching is enabled by a recurrent state-to-switch connection. An explicit duration count variable is used to improve the time-dependent switching behavior.
  arXiv  Detail & Related papers  (2021-10-26T17:35:21Z)
• Short-Term Memory Optimization in Recurrent Neural Networks by Autoencoder-based Initialization [79.42778415729475]
  We explore an alternative solution based on explicit memorization using linear autoencoders for sequences. We show how such pretraining can better support solving hard classification tasks with long sequences. We show that the proposed approach achieves a much lower reconstruction error for long sequences and a better gradient propagation during the finetuning phase.
  arXiv  Detail & Related papers  (2020-11-05T14:57:16Z)
• Implicit recurrent networks: A novel approach to stationary input processing with recurrent neural networks in deep learning [0.0]
  In this work, we introduce and test a novel implementation of recurrent neural networks into deep learning. We provide an algorithm which implements the backpropagation algorithm on a implicit implementation of recurrent networks. A single-layer implicit recurrent network is able to solve the XOR problem, while a feed-forward network with monotonically increasing activation function fails at this task.
  arXiv  Detail & Related papers  (2020-10-20T18:55:32Z)
• Improve Generalization and Robustness of Neural Networks via Weight Scale Shifting Invariant Regularizations [52.493315075385325]
  We show that a family of regularizers, including weight decay, is ineffective at penalizing the intrinsic norms of weights for networks with homogeneous activation functions. We propose an improved regularizer that is invariant to weight scale shifting and thus effectively constrains the intrinsic norm of a neural network.
  arXiv  Detail & Related papers  (2020-08-07T02:55:28Z)
• Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networks [80.15411508088522]
  Spiking neural networks (SNNs) have shown advantages over traditional artificial neural networks (ANNs) for low latency and high computational efficiency. We propose a novel ANN-to-SNN conversion and layer-wise learning framework for rapid and efficient pattern recognition.
  arXiv  Detail & Related papers  (2020-07-02T15:38:44Z)
• Continual Learning in Recurrent Neural Networks [67.05499844830231]
  We evaluate the effectiveness of continual learning methods for processing sequential data with recurrent neural networks (RNNs) We shed light on the particularities that arise when applying weight-importance methods, such as elastic weight consolidation, to RNNs. We show that the performance of weight-importance methods is not directly affected by the length of the processed sequences, but rather by high working memory requirements.
  arXiv  Detail & Related papers  (2020-06-22T10:05:12Z)
• Frequentist Uncertainty in Recurrent Neural Networks via Blockwise Influence Functions [121.10450359856242]
  Recurrent neural networks (RNNs) are instrumental in modelling sequential and time-series data. Existing approaches for uncertainty quantification in RNNs are based predominantly on Bayesian methods. We develop a frequentist alternative that: (a) does not interfere with model training or compromise its accuracy, (b) applies to any RNN architecture, and (c) provides theoretical coverage guarantees on the estimated uncertainty intervals.
  arXiv  Detail & Related papers  (2020-06-20T22:45:32Z)
• Depth Enables Long-Term Memory for Recurrent Neural Networks [0.0]
  We introduce a measure of the network's ability to support information flow across time, referred to as the Start-End separation rank. We prove that deep recurrent networks support Start-End separation ranks which are higher than those supported by their shallow counterparts.
  arXiv  Detail & Related papers  (2020-03-23T10:29:14Z)

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.