Noise Sensitivity and Stability of Deep Neural Networks for Binary Classification

• URL: http://arxiv.org/abs/2308.09374v1
• Date: Fri, 18 Aug 2023 08:09:31 GMT
• Title: Noise Sensitivity and Stability of Deep Neural Networks for Binary Classification
• Authors: Johan Jonasson, Jeffrey E. Steif and Olof Zetterqvist
• Abstract summary: We ask if certain sequences of Boolean functions represented by common DNN models are noise sensitive or noise stable. Due to the natural randomness in DNN models, these concepts are extended to annealed and quenched versions. We investigate the properties of two standard DNN architectures, the fully connected and convolutional models, when initiated with Gaussian weights.
• Score: 0.9438207505148947
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A first step is taken towards understanding often observed non-robustness phenomena of deep neural net (DNN) classifiers. This is done from the perspective of Boolean functions by asking if certain sequences of Boolean functions represented by common DNN models are noise sensitive or noise stable, concepts defined in the Boolean function literature. Due to the natural randomness in DNN models, these concepts are extended to annealed and quenched versions. Here we sort out the relation between these definitions and investigate the properties of two standard DNN architectures, the fully connected and convolutional models, when initiated with Gaussian weights.

Related papers

• Observation Noise and Initialization in Wide Neural Networks [9.163214210191814]
  We introduce a textitshifted network that enables arbitrary prior mean functions. Our theoretical insights are validated empirically, with experiments exploring different values of observation noise and network architectures.
  arXiv  Detail & Related papers  (2025-02-03T17:39:45Z)
• Novel Kernel Models and Exact Representor Theory for Neural Networks Beyond the Over-Parameterized Regime [52.00917519626559]
  This paper presents two models of neural-networks and their training applicable to neural networks of arbitrary width, depth and topology. We also present an exact novel representor theory for layer-wise neural network training with unregularized gradient descent in terms of a local-extrinsic neural kernel (LeNK) This representor theory gives insight into the role of higher-order statistics in neural network training and the effect of kernel evolution in neural-network kernel models.
  arXiv  Detail & Related papers  (2024-05-24T06:30:36Z)
• How neural networks learn to classify chaotic time series [77.34726150561087]
  We study the inner workings of neural networks trained to classify regular-versus-chaotic time series. We find that the relation between input periodicity and activation periodicity is key for the performance of LKCNN models.
  arXiv  Detail & Related papers  (2023-06-04T08:53:27Z)
• Benign Overfitting in Deep Neural Networks under Lazy Training [72.28294823115502]
  We show that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification. Our results indicate that interpolating with smoother functions leads to better generalization.
  arXiv  Detail & Related papers  (2023-05-30T19:37:44Z)
• Neural Additive Models for Location Scale and Shape: A Framework for Interpretable Neural Regression Beyond the Mean [1.0923877073891446]
  Deep neural networks (DNNs) have proven to be highly effective in a variety of tasks. Despite this success, the inner workings of DNNs are often not transparent. This lack of interpretability has led to increased research on inherently interpretable neural networks.
  arXiv  Detail & Related papers  (2023-01-27T17:06:13Z)
• Spiking Neural Networks -- Part II: Detecting Spatio-Temporal Patterns [38.518936229794214]
  Spiking Neural Networks (SNNs) have the unique ability to detect information in encoded-temporal signals. We review models and training algorithms for the dominant approach that considers SNNs as a Recurrent Neural Network (RNN) We describe an alternative approach that relies on probabilistic models for spiking neurons, allowing the derivation of local learning rules via gradient estimates.
  arXiv  Detail & Related papers  (2020-10-27T11:47:42Z)
• Stability of Algebraic Neural Networks to Small Perturbations [179.55535781816343]
  Algebraic neural networks (AlgNNs) are composed of a cascade of layers each one associated to and algebraic signal model. We show how any architecture that uses a formal notion of convolution can be stable beyond particular choices of the shift operator.
  arXiv  Detail & Related papers  (2020-10-22T09:10:16Z)
• The Surprising Power of Graph Neural Networks with Random Node Initialization [54.4101931234922]
  Graph neural networks (GNNs) are effective models for representation learning on relational data. Standard GNNs are limited in their expressive power, as they cannot distinguish beyond the capability of the Weisfeiler-Leman graph isomorphism. In this work, we analyze the expressive power of GNNs with random node (RNI) We prove that these models are universal, a first such result for GNNs not relying on computationally demanding higher-order properties.
  arXiv  Detail & Related papers  (2020-10-02T19:53:05Z)
• Binarized Graph Neural Network [65.20589262811677]
  We develop a binarized graph neural network to learn the binary representations of the nodes with binary network parameters. Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches. Experiments indicate that the proposed binarized graph neural network, namely BGN, is orders of magnitude more efficient in terms of both time and space.
  arXiv  Detail & Related papers  (2020-04-19T09:43:14Z)

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.