On Hardening DNNs against Noisy Computations

• URL: http://arxiv.org/abs/2501.14531v1
• Date: Fri, 24 Jan 2025 14:37:24 GMT
• Title: On Hardening DNNs against Noisy Computations
• Authors: Xiao Wang, Hendrik Borras, Bernhard Klein, Holger Fröning,
• Abstract summary: This work investigates the effectiveness of training neural networks with quantization to increase the robustness against noise. We compare these methods with noisy training, which incorporates a noise injection during training that mimics the noise encountered during inference.
• Score: 5.975221928631025
• License:
• Abstract: The success of deep learning has sparked significant interest in designing computer hardware optimized for the high computational demands of neural network inference. As further miniaturization of digital CMOS processors becomes increasingly challenging, alternative computing paradigms, such as analog computing, are gaining consideration. Particularly for compute-intensive tasks such as matrix multiplication, analog computing presents a promising alternative due to its potential for significantly higher energy efficiency compared to conventional digital technology. However, analog computations are inherently noisy, which makes it challenging to maintain high accuracy on deep neural networks. This work investigates the effectiveness of training neural networks with quantization to increase the robustness against noise. Experimental results across various network architectures show that quantization-aware training with constant scaling factors enhances robustness. We compare these methods with noisy training, which incorporates a noise injection during training that mimics the noise encountered during inference. While both two methods increase tolerance against noise, noisy training emerges as the superior approach for achieving robust neural network performance, especially in complex neural architectures.

Related papers

• Neuromorphic Wireless Split Computing with Multi-Level Spikes [69.73249913506042]
  Neuromorphic computing uses spiking neural networks (SNNs) to perform inference tasks. embedding a small payload within each spike exchanged between spiking neurons can enhance inference accuracy without increasing energy consumption. split computing - where an SNN is partitioned across two devices - is a promising solution. This paper presents the first comprehensive study of a neuromorphic wireless split computing architecture that employs multi-level SNNs.
  arXiv  Detail & Related papers  (2024-11-07T14:08:35Z)
• Learning Provably Robust Estimators for Inverse Problems via Jittering [51.467236126126366]
  We investigate whether jittering, a simple regularization technique, is effective for learning worst-case robust estimators for inverse problems. We show that jittering significantly enhances the worst-case robustness, but can be suboptimal for inverse problems beyond denoising.
  arXiv  Detail & Related papers  (2023-07-24T14:19:36Z)
• Walking Noise: On Layer-Specific Robustness of Neural Architectures against Noisy Computations and Associated Characteristic Learning Dynamics [1.5184189132709105]
  We discuss the implications of additive, multiplicative and mixed noise for different classification tasks and model architectures. We propose a methodology called Walking Noise which injects layer-specific noise to measure the robustness. We conclude with a discussion of the use of this methodology in practice, among others, discussing its use for tailored multi-execution in noisy environments.
  arXiv  Detail & Related papers  (2022-12-20T17:09:08Z)
• Robustness of quantum reinforcement learning under hardware errors [0.0]
  Variational quantum machine learning algorithms have become the focus of recent research on how to utilize near-term quantum devices for machine learning tasks. They are considered suitable for this as the circuits that are run can be tailored to the device, and a big part of the computation is delegated to the classical. However, the effect of training quantum machine learning models under the influence of hardware-induced noise has not yet been extensively studied.
  arXiv  Detail & Related papers  (2022-12-19T13:14:22Z)
• Optimizing Tensor Network Contraction Using Reinforcement Learning [86.05566365115729]
  We propose a Reinforcement Learning (RL) approach combined with Graph Neural Networks (GNN) to address the contraction ordering problem. The problem is extremely challenging due to the huge search space, the heavy-tailed reward distribution, and the challenging credit assignment. We show how a carefully implemented RL-agent that uses a GNN as the basic policy construct can address these challenges.
  arXiv  Detail & Related papers  (2022-04-18T21:45:13Z)
• Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference [56.24109486973292]
  We study the interplay between pruning and quantization during the training of neural networks for ultra low latency applications. We find that quantization-aware pruning yields more computationally efficient models than either pruning or quantization alone for our task.
  arXiv  Detail & Related papers  (2021-02-22T19:00:05Z)
• Robust Processing-In-Memory Neural Networks via Noise-Aware Normalization [26.270754571140735]
  PIM accelerators often suffer from intrinsic noise in the physical components. We propose a noise-agnostic method to achieve robust neural network performance against any noise setting.
  arXiv  Detail & Related papers  (2020-07-07T06:51:28Z)
• Spiking Neural Networks Hardware Implementations and Challenges: a Survey [53.429871539789445]
  Spiking Neural Networks are cognitive algorithms mimicking neuron and synapse operational principles. We present the state of the art of hardware implementations of spiking neural networks. We discuss the strategies employed to leverage the characteristics of these event-driven algorithms at the hardware level.
  arXiv  Detail & Related papers  (2020-05-04T13:24:00Z)
• Binary Neural Networks: A Survey [126.67799882857656]
  The binary neural network serves as a promising technique for deploying deep models on resource-limited devices. The binarization inevitably causes severe information loss, and even worse, its discontinuity brings difficulty to the optimization of the deep network. We present a survey of these algorithms, mainly categorized into the native solutions directly conducting binarization, and the optimized ones using techniques like minimizing the quantization error, improving the network loss function, and reducing the gradient error.
  arXiv  Detail & Related papers  (2020-03-31T16:47:20Z)
• Boolean learning under noise-perturbations in hardware neural networks [0.0]
  We find that noise strongly modifies the system's path during convergence, and surprisingly fully decorrelates the final readout weight matrices. This highlights the importance of understanding architecture, noise and learning algorithm as interacting players.
  arXiv  Detail & Related papers  (2020-03-27T10:36:03Z)
• Noisy Machines: Understanding Noisy Neural Networks and Enhancing Robustness to Analog Hardware Errors Using Distillation [12.30062870698165]
  We show how a noisy neural network has reduced learning capacity as a result of loss of mutual information between its input and output. We propose using knowledge distillation combined with noise injection during training to achieve more noise robust networks. Our method achieves models with as much as two times greater noise tolerance compared with the previous best attempts.
  arXiv  Detail & Related papers  (2020-01-14T18:59:48Z)

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.