Category-orthogonal object features guide information processing in recurrent neural networks trained for object categorization

• URL: http://arxiv.org/abs/2111.07898v1
• Date: Mon, 15 Nov 2021 16:52:07 GMT
• Title: Category-orthogonal object features guide information processing in recurrent neural networks trained for object categorization
• Authors: Sushrut Thorat, Giacomo Aldegheri, Tim C. Kietzmann
• Abstract summary: Recurrent neural networks (RNNs) have been shown to perform better than feedforward architectures in visual object categorization tasks. We test the hypothesis that recurrence iteratively aids object categorization via the communication of category-orthogonal auxiliary variables.
• Score: 0.12891210250935145
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recurrent neural networks (RNNs) have been shown to perform better than feedforward architectures in visual object categorization tasks, especially in challenging conditions such as cluttered images. However, little is known about the exact computational role of recurrent information flow in these conditions. Here we test RNNs trained for object categorization on the hypothesis that recurrence iteratively aids object categorization via the communication of category-orthogonal auxiliary variables (the location, orientation, and scale of the object). Using diagnostic linear readouts, we find that: (a) information about auxiliary variables increases across time in all network layers, (b) this information is indeed present in the recurrent information flow, and (c) its manipulation significantly affects task performance. These observations confirm the hypothesis that category-orthogonal auxiliary variable information is conveyed through recurrent connectivity and is used to optimize category inference in cluttered environments.

Related papers

• Category learning in deep neural networks: Information content and geometry of internal representations [2.1485350418225244]
  In animals, category learning enhances discrimination between stimuli close to the category boundary.<n>This phenomenon, called categorical perception, was also empirically observed in artificial neural networks trained on classification tasks.<n>We show that minimizing the Bayes cost (mean of the cross-entropy loss) implies maximizing the mutual information between the set of categories and the neural activities prior to the decision layer.
  arXiv  Detail & Related papers  (2025-10-21T19:02:51Z)
• Hidden Classification Layers: Enhancing linear separability between classes in neural networks layers [0.0]
  We investigate the impact on deep network performances of a training approach. We propose a neural network architecture which induces an error function involving the outputs of all the network layers.
  arXiv  Detail & Related papers  (2023-06-09T10:52:49Z)
• Multiclass classification for multidimensional functional data through deep neural networks [0.22843885788439797]
  We introduce a novel functional deep neural network (mfDNN) as an innovative data mining classification tool. We consider sparse deep neural network architecture with linear unit (ReLU) activation function and minimize the cross-entropy loss in the multiclass classification setup. We demonstrate the performance of mfDNN on simulated data and several benchmark datasets from different application domains.
  arXiv  Detail & Related papers  (2023-05-22T16:56:01Z)
• Isometric Representations in Neural Networks Improve Robustness [0.0]
  We train neural networks to perform classification while simultaneously maintaining within-class metric structure. We verify that isometric regularization improves the robustness to adversarial attacks on MNIST.
  arXiv  Detail & Related papers  (2022-11-02T16:18:18Z)
• Decomposing neural networks as mappings of correlation functions [57.52754806616669]
  We study the mapping between probability distributions implemented by a deep feed-forward network. We identify essential statistics in the data, as well as different information representations that can be used by neural networks.
  arXiv  Detail & Related papers  (2022-02-10T09:30:31Z)
• Convolutional generative adversarial imputation networks for spatio-temporal missing data in storm surge simulations [86.5302150777089]
  Generative Adversarial Imputation Nets (GANs) and GAN-based techniques have attracted attention as unsupervised machine learning methods. We name our proposed method as Con Conval Generative Adversarial Imputation Nets (Conv-GAIN)
  arXiv  Detail & Related papers  (2021-11-03T03:50:48Z)
• Category-Learning with Context-Augmented Autoencoder [63.05016513788047]
  Finding an interpretable non-redundant representation of real-world data is one of the key problems in Machine Learning. We propose a novel method of using data augmentations when training autoencoders. We train a Variational Autoencoder in such a way, that it makes transformation outcome predictable by auxiliary network.
  arXiv  Detail & Related papers  (2020-10-10T14:04:44Z)
• Counterfactual Explanation Based on Gradual Construction for Deep Networks [17.79934085808291]
  The patterns that deep networks have learned from a training dataset can be grasped by observing the feature variation among various classes. Current approaches perform the feature modification to increase the classification probability for the target class irrespective of the internal characteristics of deep networks. We propose a counterfactual explanation method that exploits the statistics learned from a training dataset.
  arXiv  Detail & Related papers  (2020-08-05T01:18:31Z)
• Self-Challenging Improves Cross-Domain Generalization [81.99554996975372]
  Convolutional Neural Networks (CNN) conduct image classification by activating dominant features that correlated with labels. We introduce a simple training, Self-Challenging Representation (RSC), that significantly improves the generalization of CNN to the out-of-domain data. RSC iteratively challenges the dominant features activated on the training data, and forces the network to activate remaining features that correlates with labels.
  arXiv  Detail & Related papers  (2020-07-05T21:42:26Z)
• Ventral-Dorsal Neural Networks: Object Detection via Selective Attention [51.79577908317031]
  We propose a new framework called Ventral-Dorsal Networks (VDNets) Inspired by the structure of the human visual system, we propose the integration of a "Ventral Network" and a "Dorsal Network" Our experimental results reveal that the proposed method outperforms state-of-the-art object detection approaches.
  arXiv  Detail & Related papers  (2020-05-15T23:57:36Z)
• BiDet: An Efficient Binarized Object Detector [96.19708396510894]
  We propose a binarized neural network learning method called BiDet for efficient object detection. Our BiDet fully utilizes the representational capacity of the binary neural networks for object detection by redundancy removal. Our method outperforms the state-of-the-art binary neural networks by a sizable margin.
  arXiv  Detail & Related papers  (2020-03-09T08:16:16Z)

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.