Finding Concept Representations in Neural Networks with Self-Organizing Maps

• URL: http://arxiv.org/abs/2312.05864v1
• Date: Sun, 10 Dec 2023 12:10:34 GMT
• Title: Finding Concept Representations in Neural Networks with Self-Organizing Maps
• Authors: Mathieu d'Aquin
• Abstract summary: 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.
• Score: 2.817412580574242
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In sufficiently complex tasks, it is expected that as a side effect of learning to solve a problem, a neural network will learn relevant abstractions of the representation of that problem. This has been confirmed in particular in machine vision where a number of works showed that correlations could be found between the activations of specific units (neurons) in a neural network and the visual concepts (textures, colors, objects) present in the image. Here, we explore the use of self-organizing maps as a way to both visually and computationally inspect how activation vectors of whole layers of neural networks correspond to neural representations of abstract concepts such as `female person' or `realist painter'. We experiment with multiple measures applied to those maps to assess the level of representation of a concept in a network's layer. We show that, among the measures tested, the relative entropy of the activation map for a concept compared to the map for the whole data is a suitable candidate and can be used as part of a methodology to identify and locate the neural representation of a concept, visualize it, and understand its importance in solving the prediction task at hand.

Related papers

• Identifying Sub-networks in Neural Networks via Functionally Similar Representations [41.028797971427124]
  We take a step toward automating the understanding of the network by investigating the existence of distinct sub-networks. Our approach offers meaningful insights into the behavior of neural networks with minimal human and computational cost.
  arXiv  Detail & Related papers  (2024-10-21T20:19:00Z)
• 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)
• 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)
• Formal Conceptual Views in Neural Networks [0.0]
  We introduce two notions for conceptual views of a neural network, specifically a many-valued and a symbolic view. We test the conceptual expressivity of our novel views through different experiments on the ImageNet and Fruit-360 data sets. We demonstrate how conceptual views can be applied for abductive learning of human comprehensible rules from neurons.
  arXiv  Detail & Related papers  (2022-09-27T16:38:24Z)
• Neural Activation Patterns (NAPs): Visual Explainability of Learned Concepts [8.562628320010035]
  We present a method that takes into account the entire activation distribution. By extracting similar activation profiles within the high-dimensional activation space of a neural network layer, we find groups of inputs that are treated similarly. These input groups represent neural activation patterns (NAPs) and can be used to visualize and interpret learned layer concepts.
  arXiv  Detail & Related papers  (2022-06-20T09:05:57Z)
• Functional2Structural: Cross-Modality Brain Networks Representation Learning [55.24969686433101]
  Graph mining on brain networks may facilitate the discovery of novel biomarkers for clinical phenotypes and neurodegenerative diseases. We propose a novel graph learning framework, known as Deep Signed Brain Networks (DSBN), with a signed graph encoder. We validate our framework on clinical phenotype and neurodegenerative disease prediction tasks using two independent, publicly available datasets.
  arXiv  Detail & Related papers  (2022-05-06T03:45:36Z)
• FuNNscope: Visual microscope for interactively exploring the loss landscape of fully connected neural networks [77.34726150561087]
  We show how to explore high-dimensional landscape characteristics of neural networks. We generalize observations on small neural networks to more complex systems. An interactive dashboard opens up a number of possible application networks.
  arXiv  Detail & Related papers  (2022-04-09T16:41:53Z)
• Neural Network based Successor Representations of Space and Language [6.748976209131109]
  We present a neural network based approach to learn multi-scale successor representations of structured knowledge. In all scenarios, the neural network correctly learns and approximates the underlying structure by building successor representations. We conclude that cognitive maps and neural network-based successor representations of structured knowledge provide a promising way to overcome some of the short comings of deep learning towards artificial general intelligence.
  arXiv  Detail & Related papers  (2022-02-22T21:52:46Z)
• Can the brain use waves to solve planning problems? [62.997667081978825]
  We present a neural network model which can solve such tasks. The model is compatible with a broad range of empirical findings about the mammalian neocortex and hippocampus.
  arXiv  Detail & Related papers  (2021-10-11T11:07:05Z)
• Understanding the Role of Individual Units in a Deep Neural Network [85.23117441162772]
  We present an analytic framework to systematically identify hidden units within image classification and image generation networks. First, we analyze a convolutional neural network (CNN) trained on scene classification and discover units that match a diverse set of object concepts. Second, we use a similar analytic method to analyze a generative adversarial network (GAN) model trained to generate scenes.
  arXiv  Detail & Related papers  (2020-09-10T17:59:10Z)
• 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)

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.