Half-Space Feature Learning in Neural Networks

• URL: http://arxiv.org/abs/2404.04312v1
• Date: Fri, 5 Apr 2024 12:03:19 GMT
• Title: Half-Space Feature Learning in Neural Networks
• Authors: Mahesh Lorik Yadav, Harish Guruprasad Ramaswamy, Chandrashekar Lakshminarayanan,
• Abstract summary: There currently exist two extreme viewpoints for neural network feature learning. We argue neither interpretation is likely to be correct based on a novel viewpoint. We use this alternate interpretation to motivate a model, called the Deep Linearly Gated Network (DLGN)
• Score: 2.3249139042158853
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: There currently exist two extreme viewpoints for neural network feature learning -- (i) Neural networks simply implement a kernel method (a la NTK) and hence no features are learned (ii) Neural networks can represent (and hence learn) intricate hierarchical features suitable for the data. We argue in this paper neither interpretation is likely to be correct based on a novel viewpoint. Neural networks can be viewed as a mixture of experts, where each expert corresponds to a (number of layers length) path through a sequence of hidden units. We use this alternate interpretation to motivate a model, called the Deep Linearly Gated Network (DLGN), which sits midway between deep linear networks and ReLU networks. Unlike deep linear networks, the DLGN is capable of learning non-linear features (which are then linearly combined), and unlike ReLU networks these features are ultimately simple -- each feature is effectively an indicator function for a region compactly described as an intersection of (number of layers) half-spaces in the input space. This viewpoint allows for a comprehensive global visualization of features, unlike the local visualizations for neurons based on saliency/activation/gradient maps. Feature learning in DLGNs is shown to happen and the mechanism with which this happens is through learning half-spaces in the input space that contain smooth regions of the target function. Due to the structure of DLGNs, the neurons in later layers are fundamentally the same as those in earlier layers -- they all represent a half-space -- however, the dynamics of gradient descent impart a distinct clustering to the later layer neurons. We hypothesize that ReLU networks also have similar feature learning behaviour.

Related papers

• Visualising Feature Learning in Deep Neural Networks by Diagonalizing the Forward Feature Map [4.776836972093627]
  We present a method for analysing feature learning by decomposing deep neural networks (DNNs) We find that DNNs converge to a minimal feature (MF) regime dominated by a number of eigenfunctions equal to the number of classes. We recast the phenomenon of neural collapse into a kernel picture which can be extended to broader tasks such as regression.
  arXiv  Detail & Related papers  (2024-10-05T18:53:48Z)
• 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)
• Graph Neural Networks Provably Benefit from Structural Information: A Feature Learning Perspective [53.999128831324576]
  Graph neural networks (GNNs) have pioneered advancements in graph representation learning. This study investigates the role of graph convolution within the context of feature learning theory.
  arXiv  Detail & Related papers  (2023-06-24T10:21:11Z)
• ReLU Neural Networks with Linear Layers are Biased Towards Single- and Multi-Index Models [9.96121040675476]
  This manuscript explores how properties of functions learned by neural networks of depth greater than two layers affect predictions. Our framework considers a family of networks of varying depths that all have the same capacity but different representation costs.
  arXiv  Detail & Related papers  (2023-05-24T22:10:12Z)
• Gradient Descent in Neural Networks as Sequential Learning in RKBS [63.011641517977644]
  We construct an exact power-series representation of the neural network in a finite neighborhood of the initial weights. We prove that, regardless of width, the training sequence produced by gradient descent can be exactly replicated by regularized sequential learning.
  arXiv  Detail & Related papers  (2023-02-01T03:18:07Z)
• Exploring the Approximation Capabilities of Multiplicative Neural Networks for Smooth Functions [9.936974568429173]
  We consider two classes of target functions: generalized bandlimited functions and Sobolev-Type balls. Our results demonstrate that multiplicative neural networks can approximate these functions with significantly fewer layers and neurons. These findings suggest that multiplicative gates can outperform standard feed-forward layers and have potential for improving neural network design.
  arXiv  Detail & Related papers  (2023-01-11T17:57:33Z)
• How and what to learn:The modes of machine learning [7.085027463060304]
  We propose a new approach, namely the weight pathway analysis (WPA), to study the mechanism of multilayer neural networks. WPA shows that a neural network stores and utilizes information in a "holographic" way, that is, the network encodes all training samples in a coherent structure. It is found that hidden-layer neurons self-organize into different classes in the later stages of the learning process.
  arXiv  Detail & Related papers  (2022-02-28T14:39:06Z)
• Redundant representations help generalization in wide neural networks [71.38860635025907]
  We study the last hidden layer representations of various state-of-the-art convolutional neural networks. We find that if the last hidden representation is wide enough, its neurons tend to split into groups that carry identical information, and differ from each other only by statistically independent noise.
  arXiv  Detail & Related papers  (2021-06-07T10:18:54Z)
• Exploiting Heterogeneity in Operational Neural Networks by Synaptic Plasticity [87.32169414230822]
  Recently proposed network model, Operational Neural Networks (ONNs), can generalize the conventional Convolutional Neural Networks (CNNs) In this study the focus is drawn on searching the best-possible operator set(s) for the hidden neurons of the network based on the Synaptic Plasticity paradigm that poses the essential learning theory in biological neurons. Experimental results over highly challenging problems demonstrate that the elite ONNs even with few neurons and layers can achieve a superior learning performance than GIS-based ONNs.
  arXiv  Detail & Related papers  (2020-08-21T19:03:23Z)
• Locality Guided Neural Networks for Explainable Artificial Intelligence [12.435539489388708]
  We propose a novel algorithm for back propagation, called Locality Guided Neural Network(LGNN) LGNN preserves locality between neighbouring neurons within each layer of a deep network. In our experiments, we train various VGG and Wide ResNet (WRN) networks for image classification on CIFAR100.
  arXiv  Detail & Related papers  (2020-07-12T23:45:51Z)
• Towards Understanding Hierarchical Learning: Benefits of Neural Representations [160.33479656108926]
  In this work, we demonstrate that intermediate neural representations add more flexibility to neural networks. We show that neural representation can achieve improved sample complexities compared with the raw input. Our results characterize when neural representations are beneficial, and may provide a new perspective on why depth is important in deep learning.
  arXiv  Detail & Related papers  (2020-06-24T02:44:54Z)

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.