Mechanism of feature learning in convolutional neural networks

• URL: http://arxiv.org/abs/2309.00570v1
• Date: Fri, 1 Sep 2023 16:30:02 GMT
• Title: Mechanism of feature learning in convolutional neural networks
• Authors: Daniel Beaglehole, Adityanarayanan Radhakrishnan, Parthe Pandit, Mikhail Belkin
• Abstract summary: We identify the mechanism of how convolutional neural networks learn from image data. We present empirical evidence for our ansatz, including identifying high correlation between covariances of filters and patch-based AGOPs. We then demonstrate the generality of our result by using the patch-based AGOP to enable deep feature learning in convolutional kernel machines.
• Score: 14.612673151889615
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Understanding the mechanism of how convolutional neural networks learn features from image data is a fundamental problem in machine learning and computer vision. In this work, we identify such a mechanism. We posit the Convolutional Neural Feature Ansatz, which states that covariances of filters in any convolutional layer are proportional to the average gradient outer product (AGOP) taken with respect to patches of the input to that layer. We present extensive empirical evidence for our ansatz, including identifying high correlation between covariances of filters and patch-based AGOPs for convolutional layers in standard neural architectures, such as AlexNet, VGG, and ResNets pre-trained on ImageNet. We also provide supporting theoretical evidence. We then demonstrate the generality of our result by using the patch-based AGOP to enable deep feature learning in convolutional kernel machines. We refer to the resulting algorithm as (Deep) ConvRFM and show that our algorithm recovers similar features to deep convolutional networks including the notable emergence of edge detectors. Moreover, we find that Deep ConvRFM overcomes previously identified limitations of convolutional kernels, such as their inability to adapt to local signals in images and, as a result, leads to sizable performance improvement over fixed convolutional kernels.

Related papers

• Emergence of Globally Attracting Fixed Points in Deep Neural Networks With Nonlinear Activations [24.052411316664017]
  We introduce a theoretical framework for the evolution of the kernel sequence, which measures the similarity between the hidden representation for two different inputs. For nonlinear activations, the kernel sequence converges globally to a unique fixed point, which can correspond to similar representations depending on the activation and network architecture. This work provides new insights into the implicit biases of deep neural networks and how architectural choices influence the evolution of representations across layers.
  arXiv  Detail & Related papers  (2024-10-26T07:10:47Z)
• Graph Neural Networks for Learning Equivariant Representations of Neural Networks [55.04145324152541]
  We propose to represent neural networks as computational graphs of parameters. Our approach enables a single model to encode neural computational graphs with diverse architectures. We showcase the effectiveness of our method on a wide range of tasks, including classification and editing of implicit neural representations.
  arXiv  Detail & Related papers  (2024-03-18T18:01:01Z)
• Local Kernel Renormalization as a mechanism for feature learning in overparametrized Convolutional Neural Networks [0.0]
  Empirical evidence shows that fully-connected neural networks in the infinite-width limit eventually outperform their finite-width counterparts. State-of-the-art architectures with convolutional layers achieve optimal performances in the finite-width regime. We show that the generalization performance of a finite-width FC network can be obtained by an infinite-width network, with a suitable choice of the Gaussian priors.
  arXiv  Detail & Related papers  (2023-07-21T17:22:04Z)
• Kernel function impact on convolutional neural networks [10.98068123467568]
  We study the usage of kernel functions at the different layers in a convolutional neural network. We show how one can effectively leverage kernel functions, by introducing a more distortion aware pooling layers. We propose Kernelized Dense Layers (KDL), which replace fully-connected layers.
  arXiv  Detail & Related papers  (2023-02-20T19:57:01Z)
• Inducing Gaussian Process Networks [80.40892394020797]
  We propose inducing Gaussian process networks (IGN), a simple framework for simultaneously learning the feature space as well as the inducing points. The inducing points, in particular, are learned directly in the feature space, enabling a seamless representation of complex structured domains. We report on experimental results for real-world data sets showing that IGNs provide significant advances over state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-04-21T05:27:09Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Implementing a foveal-pit inspired filter in a Spiking Convolutional Neural Network: a preliminary study [0.0]
  We have presented a Spiking Convolutional Neural Network (SCNN) that incorporates retinal foveal-pit inspired Difference of Gaussian filters and rank-order encoding. The model is trained using a variant of the backpropagation algorithm adapted to work with spiking neurons, as implemented in the Nengo library. The network has achieved up to 90% accuracy, where loss is calculated using the cross-entropy function.
  arXiv  Detail & Related papers  (2021-05-29T15:28:30Z)
• Learning Structures for Deep Neural Networks [99.8331363309895]
  We propose to adopt the efficient coding principle, rooted in information theory and developed in computational neuroscience. We show that sparse coding can effectively maximize the entropy of the output signals. Our experiments on a public image classification dataset demonstrate that using the structure learned from scratch by our proposed algorithm, one can achieve a classification accuracy comparable to the best expert-designed structure.
  arXiv  Detail & Related papers  (2021-05-27T12:27:24Z)
• Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling [79.15521784128102]
  We introduce a novel neural network for building image generators (decoders) and apply it to variational autoencoders (VAEs) In our spatial dependency networks (SDNs), feature maps at each level of a deep neural net are computed in a spatially coherent way. We show that augmenting the decoder of a hierarchical VAE by spatial dependency layers considerably improves density estimation.
  arXiv  Detail & Related papers  (2021-03-16T07:01:08Z)
• Computational optimization of convolutional neural networks using separated filters architecture [69.73393478582027]
  We consider a convolutional neural network transformation that reduces computation complexity and thus speedups neural network processing. Use of convolutional neural networks (CNN) is the standard approach to image recognition despite the fact they can be too computationally demanding.
  arXiv  Detail & Related papers  (2020-02-18T17:42:13Z)

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.