Understanding and mitigating noise in trained deep neural networks

• URL: http://arxiv.org/abs/2103.07413v3
• Date: Thu, 16 Dec 2021 15:02:09 GMT
• Title: Understanding and mitigating noise in trained deep neural networks
• Authors: Nadezhda Semenova, Laurent Larger, and Daniel Brunner
• Abstract summary: We study the propagation of noise in deep neural networks comprising noisy nonlinear neurons in trained fully connected layers. We find that noise accumulation is generally bound, and adding additional network layers does not worsen the signal to noise ratio beyond a limit. We identify criteria allowing engineers to design noise-resilient novel neural network hardware.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks unlocked a vast range of new applications by solving tasks of which many were previously deemed as reserved to higher human intelligence. One of the developments enabling this success was a boost in computing power provided by special purpose hardware, such as graphic or tensor processing units. However, these do not leverage fundamental features of neural networks like parallelism and analog state variables. Instead, they emulate neural networks relying on binary computing, which results in unsustainable energy consumption and comparatively low speed. Fully parallel and analogue hardware promises to overcome these challenges, yet the impact of analogue neuron noise and its propagation, i.e. accumulation, threatens rendering such approaches inept. Here, we determine for the first time the propagation of noise in deep neural networks comprising noisy nonlinear neurons in trained fully connected layers. We study additive and multiplicative as well as correlated and uncorrelated noise, and develop analytical methods that predict the noise level in any layer of symmetric deep neural networks or deep neural networks trained with back propagation. We find that noise accumulation is generally bound, and adding additional network layers does not worsen the signal to noise ratio beyond a limit. Most importantly, noise accumulation can be suppressed entirely when neuron activation functions have a slope smaller than unity. We therefore developed the framework for noise in fully connected deep neural networks implemented in analog systems, and identify criteria allowing engineers to design noise-resilient novel neural network hardware.

Related papers

• Impact of white noise in artificial neural networks trained for classification: performance and noise mitigation strategies [0.0]
  We consider how additive and multiplicative Gaussian white noise on the neuronal level can affect the accuracy of the network. We adapt several noise reduction techniques to the essential setting of classification tasks.
  arXiv  Detail & Related papers  (2024-11-07T01:21:12Z)
• Addressing caveats of neural persistence with deep graph persistence [54.424983583720675]
  We find that the variance of network weights and spatial concentration of large weights are the main factors that impact neural persistence. We propose an extension of the filtration underlying neural persistence to the whole neural network instead of single layers. This yields our deep graph persistence measure, which implicitly incorporates persistent paths through the network and alleviates variance-related issues.
  arXiv  Detail & Related papers  (2023-07-20T13:34:11Z)
• Benign Overfitting for Two-layer ReLU Convolutional Neural Networks [60.19739010031304]
  We establish algorithm-dependent risk bounds for learning two-layer ReLU convolutional neural networks with label-flipping noise. We show that, under mild conditions, the neural network trained by gradient descent can achieve near-zero training loss and Bayes optimal test risk.
  arXiv  Detail & Related papers  (2023-03-07T18:59:38Z)
• Spiking neural network for nonlinear regression [68.8204255655161]
  Spiking neural networks carry the potential for a massive reduction in memory and energy consumption. They introduce temporal and neuronal sparsity, which can be exploited by next-generation neuromorphic hardware. A framework for regression using spiking neural networks is proposed.
  arXiv  Detail & Related papers  (2022-10-06T13:04:45Z)
• Stochastic resonance neurons in artificial neural networks [0.0]
  We propose a new type of neural networks using resonances as an inherent part of the architecture. We show that such a neural network is more robust against the impact of noise.
  arXiv  Detail & Related papers  (2022-05-06T18:42:36Z)
• Noise mitigation strategies in physical feedforward neural networks [0.0]
  Physical neural networks are promising candidates for next generation artificial intelligence hardware. We introduce connectivity topologies, ghost neurons as well as pooling as noise mitigation strategies. We demonstrate the effectiveness of the combined methods based on a fully trained neural network classifying the MNIST handwritten digits.
  arXiv  Detail & Related papers  (2022-04-20T13:51:46Z)
• Artificial Neural Networks generated by Low Discrepancy Sequences [59.51653996175648]
  We generate artificial neural networks as random walks on a dense network graph. Such networks can be trained sparse from scratch, avoiding the expensive procedure of training a dense network and compressing it afterwards. We demonstrate that the artificial neural networks generated by low discrepancy sequences can achieve an accuracy within reach of their dense counterparts at a much lower computational complexity.
  arXiv  Detail & Related papers  (2021-03-05T08:45:43Z)
• Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting [135.0863818867184]
  artificial neural variability (ANV) helps artificial neural networks learn some advantages from natural'' neural networks. ANV plays as an implicit regularizer of the mutual information between the training data and the learned model. It can effectively relieve overfitting, label noise memorization, and catastrophic forgetting at negligible costs.
  arXiv  Detail & Related papers  (2020-11-12T06:06:33Z)
• 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)
• A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks [87.23360438947114]
  We show that noisy gradient descent with weight decay can still exhibit a " Kernel-like" behavior. This implies that the training loss converges linearly up to a certain accuracy. We also establish a novel generalization error bound for two-layer neural networks trained by noisy gradient descent with weight decay.
  arXiv  Detail & Related papers  (2020-02-10T18:56:15Z)
• 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.