Investigating the Compositional Structure Of Deep Neural Networks

• URL: http://arxiv.org/abs/2002.06967v1
• Date: Mon, 17 Feb 2020 14:16:17 GMT
• Title: Investigating the Compositional Structure Of Deep Neural Networks
• Authors: Francesco Craighero, Fabrizio Angaroni, Alex Graudenzi, Fabio Stella, Marco Antoniotti
• Abstract summary: We introduce a novel theoretical framework based on the compositional structure of piecewise linear activation functions. It is possible to characterize the instances of the input data with respect to both the predicted label and the specific (linear) transformation used to perform predictions. Preliminary tests on the MNIST dataset show that our method can group input instances with regard to their similarity in the internal representation of the neural network.
• Score: 1.8899300124593645
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The current understanding of deep neural networks can only partially explain how input structure, network parameters and optimization algorithms jointly contribute to achieve the strong generalization power that is typically observed in many real-world applications. In order to improve the comprehension and interpretability of deep neural networks, we here introduce a novel theoretical framework based on the compositional structure of piecewise linear activation functions. By defining a direct acyclic graph representing the composition of activation patterns through the network layers, it is possible to characterize the instances of the input data with respect to both the predicted label and the specific (linear) transformation used to perform predictions. Preliminary tests on the MNIST dataset show that our method can group input instances with regard to their similarity in the internal representation of the neural network, providing an intuitive measure of input complexity.

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)
• Credit Assignment for Trained Neural Networks Based on Koopman Operator Theory [3.130109807128472]
  Credit assignment problem of neural networks refers to evaluating the credit of each network component to the final outputs. This paper presents an alternative perspective of linear dynamics on dealing with the credit assignment problem for trained neural networks. Experiments conducted on typical neural networks demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2022-12-02T06:34:27Z)
• Seeking Interpretability and Explainability in Binary Activated Neural Networks [2.828173677501078]
  We study the use of binary activated neural networks as interpretable and explainable predictors in the context of regression tasks. We present an approach based on the efficient computation of SHAP values for quantifying the relative importance of the features, hidden neurons and even weights.
  arXiv  Detail & Related papers  (2022-09-07T20:11:17Z)
• The Influence of Network Structural Preference on Node Classification and Link Prediction [0.0]
  This work introduces a new feature abstraction method, namely the Transition Probabilities Matrix (TPM) The success of the proposed embedding method is tested on node identification/classification and link prediction on three commonly used real-world networks.
  arXiv  Detail & Related papers  (2022-08-07T12:56:28Z)
• Learning Dynamics and Structure of Complex Systems Using Graph Neural Networks [13.509027957413409]
  We trained graph neural networks to fit time series from an example nonlinear dynamical system. We found simple interpretations of the learned representation and model components. We successfully identified a graph translator' between the statistical interactions in belief propagation and parameters of the corresponding trained network.
  arXiv  Detail & Related papers  (2022-02-22T15:58:16Z)
• 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)
• 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)
• Learning Connectivity of Neural Networks from a Topological Perspective [80.35103711638548]
  We propose a topological perspective to represent a network into a complete graph for analysis. By assigning learnable parameters to the edges which reflect the magnitude of connections, the learning process can be performed in a differentiable manner. This learning process is compatible with existing networks and owns adaptability to larger search spaces and different tasks.
  arXiv  Detail & Related papers  (2020-08-19T04:53:31Z)
• Neural networks adapting to datasets: learning network size and topology [77.34726150561087]
  We introduce a flexible setup allowing for a neural network to learn both its size and topology during the course of a gradient-based training. The resulting network has the structure of a graph tailored to the particular learning task and dataset.
  arXiv  Detail & Related papers  (2020-06-22T12:46:44Z)
• Input-to-State Representation in linear reservoirs dynamics [15.491286626948881]
  Reservoir computing is a popular approach to design recurrent neural networks. The working principle of these networks is not fully understood. A novel analysis of the dynamics of such networks is proposed.
  arXiv  Detail & Related papers  (2020-03-24T00:14:25Z)
• Understanding Generalization in Deep Learning via Tensor Methods [53.808840694241]
  We advance the understanding of the relations between the network's architecture and its generalizability from the compression perspective. We propose a series of intuitive, data-dependent and easily-measurable properties that tightly characterize the compressibility and generalizability of neural networks.
  arXiv  Detail & Related papers  (2020-01-14T22:26:57Z)

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.