Extracting low-dimensional psychological representations from convolutional neural networks

• URL: http://arxiv.org/abs/2005.14363v1
• Date: Fri, 29 May 2020 01:29:39 GMT
• Title: Extracting low-dimensional psychological representations from convolutional neural networks
• Authors: Aditi Jha, Joshua Peterson, Thomas L. Griffiths
• Abstract summary: We present a method for reducing neural network representations to a low-dimensional space which is still predictive of similarity judgments. We show that these low-dimensional representations also provide insightful explanations of factors underlying human similarity judgments.
• Score: 10.269997499911666
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks are increasingly being used in cognitive modeling as a means of deriving representations for complex stimuli such as images. While the predictive power of these networks is high, it is often not clear whether they also offer useful explanations of the task at hand. Convolutional neural network representations have been shown to be predictive of human similarity judgments for images after appropriate adaptation. However, these high-dimensional representations are difficult to interpret. Here we present a method for reducing these representations to a low-dimensional space which is still predictive of similarity judgments. We show that these low-dimensional representations also provide insightful explanations of factors underlying human similarity judgments.

Related papers

• Local vs distributed representations: What is the right basis for interpretability? [19.50614357801837]
  We show that features obtained from sparse distributed representations are easier to interpret by human observers. Our results highlight that distributed representations constitute a superior basis for interpretability.
  arXiv  Detail & Related papers  (2024-11-06T15:34:57Z)
• Coding schemes in neural networks learning classification tasks [52.22978725954347]
  We investigate fully-connected, wide neural networks learning classification tasks. We show that the networks acquire strong, data-dependent features. Surprisingly, the nature of the internal representations depends crucially on the neuronal nonlinearity.
  arXiv  Detail & Related papers  (2024-06-24T14:50:05Z)
• Finding Concept Representations in Neural Networks with Self-Organizing Maps [2.817412580574242]
  We show how self-organizing maps can be used to inspect how activation of layers of neural networks correspond to neural representations of abstract concepts. We show that, among the measures tested, the relative entropy of the activation map for a concept is a suitable candidate and can be used as part of a methodology to identify and locate the neural representation of a concept.
  arXiv  Detail & Related papers  (2023-12-10T12:10:34Z)
• Image segmentation with traveling waves in an exactly solvable recurrent neural network [71.74150501418039]
  We show that a recurrent neural network can effectively divide an image into groups according to a scene's structural characteristics. We present a precise description of the mechanism underlying object segmentation in this network. We then demonstrate a simple algorithm for object segmentation that generalizes across inputs ranging from simple geometric objects in grayscale images to natural images.
  arXiv  Detail & Related papers  (2023-11-28T16:46:44Z)
• Seeing in Words: Learning to Classify through Language Bottlenecks [59.97827889540685]
  Humans can explain their predictions using succinct and intuitive descriptions. We show that a vision model whose feature representations are text can effectively classify ImageNet images.
  arXiv  Detail & Related papers  (2023-06-29T00:24:42Z)
• Searching for the Essence of Adversarial Perturbations [73.96215665913797]
  We show that adversarial perturbations contain human-recognizable information, which is the key conspirator responsible for a neural network's erroneous prediction. This concept of human-recognizable information allows us to explain key features related to adversarial perturbations.
  arXiv  Detail & Related papers  (2022-05-30T18:04:57Z)
• Aesthetics and neural network image representations [0.0]
  We analyze the spaces of images encoded by generative neural networks of the BigGAN architecture. We find that generic multiplicative perturbations of neural network parameters away from the photo-realistic point often lead to networks generating images which appear as "artistic renditions" of the corresponding objects.
  arXiv  Detail & Related papers  (2021-09-16T16:50:22Z)
• A neural anisotropic view of underspecification in deep learning [60.119023683371736]
  We show that the way neural networks handle the underspecification of problems is highly dependent on the data representation. Our results highlight that understanding the architectural inductive bias in deep learning is fundamental to address the fairness, robustness, and generalization of these systems.
  arXiv  Detail & Related papers  (2021-04-29T14:31:09Z)
• Transforming Neural Network Visual Representations to Predict Human Judgments of Similarity [12.5719993304358]
  We investigate how to bring machine visual representations into better alignment with human representations. We find that with appropriate linear transformations of deep embeddings, we can improve prediction of human binary choice.
  arXiv  Detail & Related papers  (2020-10-13T16:09:47Z)
• The Representation Theory of Neural Networks [7.724617675868718]
  We show that neural networks can be represented via the mathematical theory of quiver representations. We show that network quivers gently adapt to common neural network concepts. We also provide a quiver representation model to understand how a neural network creates representations from the data.
  arXiv  Detail & Related papers  (2020-07-23T19:02:14Z)
• Towards Achieving Adversarial Robustness by Enforcing Feature Consistency Across Bit Planes [51.31334977346847]
  We train networks to form coarse impressions based on the information in higher bit planes, and use the lower bit planes only to refine their prediction. We demonstrate that, by imposing consistency on the representations learned across differently quantized images, the adversarial robustness of networks improves significantly.
  arXiv  Detail & Related papers  (2020-04-01T09:31:10Z)

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.