Energy-Efficient Stochastic Computing (SC) Neural Networks for Internet of Things Devices With Layer-Wise Adjustable Sequence Length (ASL)

• URL: http://arxiv.org/abs/2508.09163v1
• Date: Tue, 05 Aug 2025 16:45:24 GMT
• Title: Energy-Efficient Stochastic Computing (SC) Neural Networks for Internet of Things Devices With Layer-Wise Adjustable Sequence Length (ASL)
• Abstract summary: Adjustable Sequence Length (ASL) is a novel scheme that applies mixed-precision concepts specifically to neural networks (NNs)<n>This article introduces ASL, a novel scheme that applies mixed-precision concepts specifically to SC NNs.<n> Evaluations on a pipelined SC synthesized at 32nm demonstrate that ASL can reduce energy and latency overheads by up to 60% over with negligible accuracy loss.
• Score: 12.43648551511862
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Stochastic computing (SC) has emerged as an efficient low-power alternative for deploying neural networks (NNs) in resource-limited scenarios, such as the Internet of Things (IoT). By encoding values as serial bitstreams, SC significantly reduces energy dissipation compared to conventional floating-point (FP) designs; however, further improvement of layer-wise mixed-precision implementation for SC remains unexplored. This article introduces Adjustable Sequence Length (ASL), a novel scheme that applies mixed-precision concepts specifically to SC NNs. By introducing an operator-norm-based theoretical model, this article shows that truncation noise can cumulatively propagate through the layers by the estimated amplification factors. An extended sensitivity analysis is presented, using random forest (RF) regression to evaluate multilayer truncation effects and validate the alignment of theoretical predictions with practical network behaviors. To accommodate different application scenarios, this article proposes two truncation strategies (coarse-grained and fine-grained), which apply diverse sequence length configurations at each layer. Evaluations on a pipelined SC MLP synthesized at 32nm demonstrate that ASL can reduce energy and latency overheads by up to over 60% with negligible accuracy loss. It confirms the feasibility of the ASL scheme for IoT applications and highlights the distinct advantages of mixed-precision truncation in SC designs.

Related papers

• Reducing ANN-SNN Conversion Error via Residual Membrane Potential Alignment [52.910770415431244]
  Spiking Neural Networks (SNNs) serve as core architectures for neuromorphic computing.<n>ANN-SNN conversion circumvents issues by reusing well-trained ANN weights for low-latency, energy-efficient inference.<n>Existing conversion schemes suffer from severe accuracy drops at small timesteps, large inference delays and cumulative quantization errors.
  arXiv  Detail & Related papers  (2026-08-14T04:46:03Z)
• Spiking Layer-Adaptive Magnitude-based Pruning [2.141079906482723]
  Spiking Neural Networks (SNNs) provide energy-efficient computation but their deployment is constrained by dense connectivity and high spiking operation costs.<n>This paper proposes Spiking Layer-Adaptive Magnitude-based Pruning (SLAMP)<n>SLAMP generalizes layer-adaptive magnitude pruning to temporal SNNs by explicitly controlling worst-case output distortion across layers and timesteps.
  arXiv  Detail & Related papers  (2026-03-16T07:55:57Z)
• Data-Driven Deep MIMO Detection:Network Architectures and Generalization Analysis [50.20709408241935]
  This paper proposes inspecting the fully data-driven DeepSIC detection within a Network-of-MLPs architecture.<n>Within such an architecture, DeepSIC can be upgraded as a graph-based message-passing process using Graph Neural Networks (GNNs)<n>GNNSIC achieves excellent expressivity comparable to DeepSIC with substantially fewer trainable parameters.
  arXiv  Detail & Related papers  (2026-02-13T04:38:51Z)
• Controllable Probabilistic Forecasting with Stochastic Decomposition Layers [1.3995263206621]
  We introduce Decomposition Layers (SDL) for converting deterministic machine learning weather models into ensemble systems.<n>SDL applies learned perturbations at three decoder scales through latent-driven modulation, per-pixel noise, and channel scaling.<n>When applied to WXFormer via transfer learning, SDL requires less than 2% of the computational cost needed to train the baseline model.
  arXiv  Detail & Related papers  (2025-12-21T17:10:00Z)
• (Sometimes) Less is More: Mitigating the Complexity of Rule-based Representation for Interpretable Classification [1.6504157612470989]
  Deep neural networks are widely used in practical applications of AI, but their inner structure and complexity made them generally not easily interpretable.<n>In this work, a differentiable approximation of $L_0$ regularization is adapted into a logic-based neural network, the Multi-layer Logical Perceptron (MLLP), to study its efficacy in reducing the complexity of its discrete interpretable version, the Concept Rule Set (CRS)<n>The results are compared to alternatives like Random Binarization of the network weights, to determine if better results can be achieved when using a less-noisy technique that sparsifies the
  arXiv  Detail & Related papers  (2025-09-26T14:13:08Z)
• Neural Channel Knowledge Map Assisted Scheduling Optimization of Active IRSs in Multi-User Systems [12.366506331526201]
  Intelligent Reflecting Surfaces (IRSs) have potential for significant performance gains in next-generation wireless networks.<n>IRSs face key challenges, notably severe double-pathloss and complex multi-user scheduling due to hardware constraints.<n>This paper proposes a novel scheduling framework based on neural Channel Knowledge Map (CKM)
  arXiv  Detail & Related papers  (2025-08-09T15:14:03Z)
• Hyperpruning: Efficient Search through Pruned Variants of Recurrent Neural Networks Leveraging Lyapunov Spectrum [7.136205674624814]
  We introduce an efficient hyperpruning framework, termed LS-based Hyperpruning (LSH)<n>LS-based Hyperpruning reduces search time by an order of magnitude compared to conventional approaches relying on full training.
  arXiv  Detail & Related papers  (2025-06-09T17:49:29Z)
• Optimization of Layer Skipping and Frequency Scaling for Convolutional Neural Networks under Latency Constraint [6.6947001137138455]
  We propose an approach involving Proportional Layer Skipping (PLS) and adjusts Frequency Scaling (FS)<n>PLS reduces computational complexity by selectively bypassing network layers, whereas frequency scaling the frequency of the processor to optimize energy use under latency constraints.<n>Experiments on ResNet-152 with the CIFAR-10 dataset demonstrated significant reductions in computational demands and energy consumption with minimal accuracy loss.
  arXiv  Detail & Related papers  (2025-03-31T12:40:11Z)
• Concurrent Training and Layer Pruning of Deep Neural Networks [0.0]
  We propose an algorithm capable of identifying and eliminating irrelevant layers of a neural network during the early stages of training. We employ a structure using residual connections around nonlinear network sections that allow the flow of information through the network once a nonlinear section is pruned.
  arXiv  Detail & Related papers  (2024-06-06T23:19:57Z)
• Optimization Guarantees of Unfolded ISTA and ADMM Networks With Smooth Soft-Thresholding [57.71603937699949]
  We study optimization guarantees, i.e., achieving near-zero training loss with the increase in the number of learning epochs. We show that the threshold on the number of training samples increases with the increase in the network width.
  arXiv  Detail & Related papers  (2023-09-12T13:03:47Z)
• Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution [91.3781512926942]
  Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. This work investigates the potential of network pruning for super-resolution iteration to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. We propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly network at each and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly.
  arXiv  Detail & Related papers  (2023-03-16T21:06:13Z)
• Unifying Synergies between Self-supervised Learning and Dynamic Computation [53.66628188936682]
  We present a novel perspective on the interplay between SSL and DC paradigms. We show that it is feasible to simultaneously learn a dense and gated sub-network from scratch in a SSL setting. The co-evolution during pre-training of both dense and gated encoder offers a good accuracy-efficiency trade-off.
  arXiv  Detail & Related papers  (2023-01-22T17:12:58Z)
• Learning k-Level Structured Sparse Neural Networks Using Group Envelope Regularization [4.0554893636822]
  We introduce a novel approach to deploy large-scale Deep Neural Networks on constrained resources. The method speeds up inference time and aims to reduce memory demand and power consumption.
  arXiv  Detail & Related papers  (2022-12-25T15:40:05Z)
• VQ-T: RNN Transducers using Vector-Quantized Prediction Network States [52.48566999668521]
  We propose to use vector-quantized long short-term memory units in the prediction network of RNN transducers. By training the discrete representation jointly with the ASR network, hypotheses can be actively merged for lattice generation. Our experiments on the Switchboard corpus show that the proposed VQ RNN transducers improve ASR performance over transducers with regular prediction networks.
  arXiv  Detail & Related papers  (2022-08-03T02:45:52Z)
• PAMS: Quantized Super-Resolution via Parameterized Max Scale [84.55675222525608]
  Deep convolutional neural networks (DCNNs) have shown dominant performance in the task of super-resolution (SR) We propose a new quantization scheme termed PArameterized Max Scale (PAMS), which applies the trainable truncated parameter to explore the upper bound of the quantization range adaptively. Experiments demonstrate that the proposed PAMS scheme can well compress and accelerate the existing SR models such as EDSR and RDN.
  arXiv  Detail & Related papers  (2020-11-09T06:16:05Z)

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.