Empirical Studies on the Properties of Linear Regions in Deep Neural Networks

• URL: http://arxiv.org/abs/2001.01072v3
• Date: Tue, 28 Apr 2020 19:08:06 GMT
• Title: Empirical Studies on the Properties of Linear Regions in Deep Neural Networks
• Authors: Xiao Zhang and Dongrui Wu
• Abstract summary: A deep neural network (DNN) with piecewise linear activations can partition the input space into numerous small linear regions. It is believed that the number of these regions represents the expressivity of the DNN. We study their local properties, such as the inspheres, the directions of the corresponding hyperplanes, the decision boundaries, and the relevance of the surrounding regions.
• Score: 34.08593191989188
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A deep neural network (DNN) with piecewise linear activations can partition the input space into numerous small linear regions, where different linear functions are fitted. It is believed that the number of these regions represents the expressivity of the DNN. This paper provides a novel and meticulous perspective to look into DNNs: Instead of just counting the number of the linear regions, we study their local properties, such as the inspheres, the directions of the corresponding hyperplanes, the decision boundaries, and the relevance of the surrounding regions. We empirically observed that different optimization techniques lead to completely different linear regions, even though they result in similar classification accuracies. We hope our study can inspire the design of novel optimization techniques, and help discover and analyze the behaviors of DNNs.

Related papers

• Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations [54.17275171325324]
  We present a counterexample to the Linear Representation Hypothesis (LRH) When trained to repeat an input token sequence, neural networks learn to represent the token at each position with a particular order of magnitude, rather than a direction. These findings strongly indicate that interpretability research should not be confined to the LRH.
  arXiv  Detail & Related papers  (2024-08-20T15:04:37Z)
• The Evolution of the Interplay Between Input Distributions and Linear Regions in Networks [20.97553518108504]
  We count the number of linear convex regions in deep neural networks based on ReLU. In particular, we prove that for any one-dimensional input, there exists a minimum threshold for the number of neurons required to express it. We also unveil the iterative refinement process of decision boundaries in ReLU networks during training.
  arXiv  Detail & Related papers  (2023-10-28T15:04:53Z)
• Learning Low Dimensional State Spaces with Overparameterized Recurrent Neural Nets [57.06026574261203]
  We provide theoretical evidence for learning low-dimensional state spaces, which can also model long-term memory. Experiments corroborate our theory, demonstrating extrapolation via learning low-dimensional state spaces with both linear and non-linear RNNs.
  arXiv  Detail & Related papers  (2022-10-25T14:45:15Z)
• Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study [55.12108376616355]
  The study on NTK has been devoted to typical neural network architectures, but is incomplete for neural networks with Hadamard products (NNs-Hp) In this work, we derive the finite-width-K formulation for a special class of NNs-Hp, i.e., neural networks. We prove their equivalence to the kernel regression predictor with the associated NTK, which expands the application scope of NTK.
  arXiv  Detail & Related papers  (2022-09-16T06:36:06Z)
• On the Number of Regions of Piecewise Linear Neural Networks [16.78532039510369]
  Many feedforward neural networks (NNs) generate continuous and piecewise-linear (CPWL) mappings. The number of these so-called linear regions offers a natural metric to characterize the expressiveness of CPWL NNs. We introduce a complementary framework to estimate the average number of linear regions produced by a CPWL NN.
  arXiv  Detail & Related papers  (2022-06-17T08:17:28Z)
• Lower and Upper Bounds for Numbers of Linear Regions of Graph Convolutional Networks [11.338307976409707]
  The number of linear regions has been considered a good measure for the expressivity of neural networks with piecewise linear activation. We present some estimates for the number of linear regions of the classic graph convolutional networks (GCNs) with one layer and multiple-layer scenarios.
  arXiv  Detail & Related papers  (2022-06-01T04:32:23Z)
• Exploring Linear Feature Disentanglement For Neural Networks [63.20827189693117]
  Non-linear activation functions, e.g., Sigmoid, ReLU, and Tanh, have achieved great success in neural networks (NNs) Due to the complex non-linear characteristic of samples, the objective of those activation functions is to project samples from their original feature space to a linear separable feature space. This phenomenon ignites our interest in exploring whether all features need to be transformed by all non-linear functions in current typical NNs.
  arXiv  Detail & Related papers  (2022-03-22T13:09:17Z)
• DISCO Verification: Division of Input Space into COnvex polytopes for neural network verification [0.0]
  The impressive results of modern neural networks partly come from their non linear behaviour. We propose a method to simplify the verification problem by operating a partitionning into multiple linear subproblems. We also present the impact of a technique aiming at reducing the number of linear regions during training.
  arXiv  Detail & Related papers  (2021-05-17T12:40:51Z)
• Online Limited Memory Neural-Linear Bandits with Likelihood Matching [53.18698496031658]
  We study neural-linear bandits for solving problems where both exploration and representation learning play an important role. We propose a likelihood matching algorithm that is resilient to catastrophic forgetting and is completely online.
  arXiv  Detail & Related papers  (2021-02-07T14:19:07Z)
• Bounding The Number of Linear Regions in Local Area for Neural Networks with ReLU Activations [6.4817648240626005]
  We present the first method to estimate the upper bound of the number of linear regions in any sphere in the input space of a given ReLU neural network. Our experiments showed that, while training a neural network, the boundaries of the linear regions tend to move away from the training data points.
  arXiv  Detail & Related papers  (2020-07-14T04:06:00Z)

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.