A Measure of the Complexity of Neural Representations based on Partial Information Decomposition

• URL: http://arxiv.org/abs/2209.10438v2
• Date: Wed, 17 May 2023 18:13:50 GMT
• Title: A Measure of the Complexity of Neural Representations based on Partial Information Decomposition
• Authors: David A. Ehrlich, Andreas C. Schneider, Viola Priesemann, Michael Wibral, Abdullah Makkeh
• Abstract summary: In neural networks, task-relevant information is represented jointly by groups of neurons. We show how Partial Information Decomposition (PID), a recent extension of information theory, can disentangle these different contributions. We introduce the measure of "Representational Complexity", which quantifies the difficulty of accessing information spread across multiple neurons.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In neural networks, task-relevant information is represented jointly by groups of neurons. However, the specific way in which this mutual information about the classification label is distributed among the individual neurons is not well understood: While parts of it may only be obtainable from specific single neurons, other parts are carried redundantly or synergistically by multiple neurons. We show how Partial Information Decomposition (PID), a recent extension of information theory, can disentangle these different contributions. From this, we introduce the measure of "Representational Complexity", which quantifies the difficulty of accessing information spread across multiple neurons. We show how this complexity is directly computable for smaller layers. For larger layers, we propose subsampling and coarse-graining procedures and prove corresponding bounds on the latter. Empirically, for quantized deep neural networks solving the MNIST and CIFAR10 tasks, we observe that representational complexity decreases both through successive hidden layers and over training, and compare the results to related measures. Overall, we propose representational complexity as a principled and interpretable summary statistic for analyzing the structure and evolution of neural representations and complex systems in general.

Related papers

• Relational Composition in Neural Networks: A Survey and Call to Action [54.47858085003077]
  Many neural nets appear to represent data as linear combinations of "feature vectors" We argue that this success is incomplete without an understanding of relational composition.
  arXiv  Detail & Related papers  (2024-07-19T20:50:57Z)
• Identifying Interpretable Visual Features in Artificial and Biological Neural Systems [3.604033202771937]
  Single neurons in neural networks are often interpretable in that they represent individual, intuitively meaningful features. Many neurons exhibit $textitmixed selectivity$, i.e., they represent multiple unrelated features. We propose an automated method for quantifying visual interpretability and an approach for finding meaningful directions in network activation space.
  arXiv  Detail & Related papers  (2023-10-17T17:41:28Z)
• Unsupervised Learning of Invariance Transformations [105.54048699217668]
  We develop an algorithmic framework for finding approximate graph automorphisms. We discuss how this framework can be used to find approximate automorphisms in weighted graphs in general.
  arXiv  Detail & Related papers  (2023-07-24T17:03:28Z)
• Bayes Complexity of Learners vs Overfitting [4.873362301533825]
  We show that a new notion of complexity of functions governs a PAC Bayes-like generalization bound. In contrast to previous works, our notion naturally generalizes to neural networks with several layers. An upper-bound we derive allows to show a separation in the number of samples needed for good generalization between 2 and 4-layer neural networks.
  arXiv  Detail & Related papers  (2023-03-13T13:07:02Z)
• Higher-order mutual information reveals synergistic sub-networks for multi-neuron importance [0.483420384410068]
  Previous work primarily attributed importance to individual neurons. In this work, we study which groups of neurons contain synergistic or redundant information. Results suggest our method can be used for pruning and unsupervised representation learning.
  arXiv  Detail & Related papers  (2022-11-01T12:21:15Z)
• Synergistic information supports modality integration and flexible learning in neural networks solving multiple tasks [107.8565143456161]
  We investigate the information processing strategies adopted by simple artificial neural networks performing a variety of cognitive tasks. Results show that synergy increases as neural networks learn multiple diverse tasks. randomly turning off neurons during training through dropout increases network redundancy, corresponding to an increase in robustness.
  arXiv  Detail & Related papers  (2022-10-06T15:36:27Z)
• Detecting Modularity in Deep Neural Networks [8.967870619902211]
  We consider the problem of assessing the modularity exhibited by a partitioning of a network's neurons. We propose two proxies for this: importance, which reflects how crucial sets of neurons are to network performance; and coherence, which reflects how consistently their neurons associate with features of the inputs. We show that these partitionings, even ones based only on weights, reveal groups of neurons that are important and coherent.
  arXiv  Detail & Related papers  (2021-10-13T20:33:30Z)
• The Separation Capacity of Random Neural Networks [78.25060223808936]
  We show that a sufficiently large two-layer ReLU-network with standard Gaussian weights and uniformly distributed biases can solve this problem with high probability. We quantify the relevant structure of the data in terms of a novel notion of mutual complexity.
  arXiv  Detail & Related papers  (2021-07-31T10:25:26Z)
• 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)
• Compositional Explanations of Neurons [52.71742655312625]
  We describe a procedure for explaining neurons in deep representations by identifying compositional logical concepts. We use this procedure to answer several questions on interpretability in models for vision and natural language processing.
  arXiv  Detail & Related papers  (2020-06-24T20:37:05Z)

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.