ExSpliNet: An interpretable and expressive spline-based neural network

• URL: http://arxiv.org/abs/2205.01510v1
• Date: Tue, 3 May 2022 14:06:36 GMT
• Title: ExSpliNet: An interpretable and expressive spline-based neural network
• Authors: Daniele Fakhoury, Emanuele Fakhoury and Hendrik Speleers
• Abstract summary: We present ExSpliNet, an interpretable and expressive neural network model. We give a probabilistic interpretation of the model and show its universal approximation properties.
• Score: 0.3867363075280544
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper we present ExSpliNet, an interpretable and expressive neural network model. The model combines ideas of Kolmogorov neural networks, ensembles of probabilistic trees, and multivariate B-spline representations. We give a probabilistic interpretation of the model and show its universal approximation properties. We also discuss how it can be efficiently encoded by exploiting B-spline properties. Finally, we test the effectiveness of the proposed model on synthetic approximation problems and classical machine learning benchmark datasets.

Related papers

• Estimating Causal Effects from Learned Causal Networks [56.14597641617531]
  We propose an alternative paradigm for answering causal-effect queries over discrete observable variables. We learn the causal Bayesian network and its confounding latent variables directly from the observational data. We show that this emphmodel completion learning approach can be more effective than estimand approaches.
  arXiv  Detail & Related papers  (2024-08-26T08:39:09Z)
• 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)
• This Probably Looks Exactly Like That: An Invertible Prototypical Network [8.957872207471311]
  Prototypical neural networks represent an exciting way forward in realizing human-comprehensible machine learning without concept annotations. We find that reliance on indirect interpretation functions for prototypical explanations imposes a severe limit on prototypes' informative power. We propose one such model, called ProtoFlow, by composing a normalizing flow with Gaussian mixture models.
  arXiv  Detail & Related papers  (2024-07-16T21:51:02Z)
• 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)
• Manipulating Feature Visualizations with Gradient Slingshots [54.31109240020007]
  We introduce a novel method for manipulating Feature Visualization (FV) without significantly impacting the model's decision-making process. We evaluate the effectiveness of our method on several neural network models and demonstrate its capabilities to hide the functionality of arbitrarily chosen neurons.
  arXiv  Detail & Related papers  (2024-01-11T18:57:17Z)
• Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks [25.132159381873656]
  We introduce Graph-Induced Sum-Product Networks (GSPNs), a new probabilistic framework for graph representation learning. We show the model's competitiveness on scarce supervision scenarios, under missing data, and for graph classification in comparison to popular neural models.
  arXiv  Detail & Related papers  (2023-05-17T20:02:08Z)
• Batch-Ensemble Stochastic Neural Networks for Out-of-Distribution Detection [55.028065567756066]
  Out-of-distribution (OOD) detection has recently received much attention from the machine learning community due to its importance in deploying machine learning models in real-world applications. In this paper we propose an uncertainty quantification approach by modelling the distribution of features. We incorporate an efficient ensemble mechanism, namely batch-ensemble, to construct the batch-ensemble neural networks (BE-SNNs) and overcome the feature collapse problem. We show that BE-SNNs yield superior performance on several OOD benchmarks, such as the Two-Moons dataset, the FashionMNIST vs MNIST dataset, FashionM
  arXiv  Detail & Related papers  (2022-06-26T16:00:22Z)
• PAC-Bayesian Learning of Aggregated Binary Activated Neural Networks with Probabilities over Representations [2.047424180164312]
  We study the expectation of a probabilistic neural network as a predictor by itself, focusing on the aggregation of binary activated neural networks with normal distributions over real-valued weights. We show that the exact computation remains tractable for deep but narrow neural networks, thanks to a dynamic programming approach.
  arXiv  Detail & Related papers  (2021-10-28T14:11:07Z)
• Fully differentiable model discovery [0.0]
  We propose an approach by combining neural network based surrogates with Sparse Bayesian Learning. Our work expands PINNs to various types of neural network architectures, and connects neural network-based surrogates to the rich field of Bayesian parameter inference.
  arXiv  Detail & Related papers  (2021-06-09T08:11:23Z)
• DebiNet: Debiasing Linear Models with Nonlinear Overparameterized Neural Networks [11.04121146441257]
  We incorporate over- parameterized neural networks into semi-parametric models to bridge the gap between inference and prediction. We show the theoretical foundations that make this possible and demonstrate with numerical experiments. We propose a framework, DebiNet, in which we plug-in arbitrary feature selection methods to our semi-parametric neural network.
  arXiv  Detail & Related papers  (2020-11-01T04:12:53Z)
• Explaining and Improving Model Behavior with k Nearest Neighbor Representations [107.24850861390196]
  We propose using k nearest neighbor representations to identify training examples responsible for a model's predictions. We show that kNN representations are effective at uncovering learned spurious associations. Our results indicate that the kNN approach makes the finetuned model more robust to adversarial inputs.
  arXiv  Detail & Related papers  (2020-10-18T16:55:25Z)

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.