Uninorm-like parametric activation functions for human-understandable neural models

• URL: http://arxiv.org/abs/2205.06547v1
• Date: Fri, 13 May 2022 10:25:02 GMT
• Title: Uninorm-like parametric activation functions for human-understandable neural models
• Authors: Orsolya Csisz\'ar, Luca S\'ara Pusztah\'azi, Lehel D\'enes-Fazakas, Michael S. Gashler, Vladik Kreinovich, G\'abor Csisz\'ar
• Abstract summary: We present a deep learning model for finding human-understandable connections between input features. Our approach uses a parameterized, differentiable activation function, based on the theoretical background of fuzzy logic and multi-criteria decision-making. We demonstrate the utility and effectiveness of the model by successfully applying it to classification problems from the UCI Machine Learning Repository.
• Score: 0.8808021343665319
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We present a deep learning model for finding human-understandable connections between input features. Our approach uses a parameterized, differentiable activation function, based on the theoretical background of nilpotent fuzzy logic and multi-criteria decision-making (MCDM). The learnable parameter has a semantic meaning indicating the level of compensation between input features. The neural network determines the parameters using gradient descent to find human-understandable relationships between input features. We demonstrate the utility and effectiveness of the model by successfully applying it to classification problems from the UCI Machine Learning Repository.

Related papers

• Disentangled Representation Learning for Parametric Partial Differential Equations [31.240283037552427]
  We propose a new paradigm for learning disentangled representations from neural operator parameters. DisentangO is a novel hyper-neural operator architecture designed to unveil and disentangle the latent physical factors of variation embedded within the black-box neural operator parameters. We show that DisentangO effectively extracts meaningful and interpretable latent features, bridging the divide between predictive performance and physical understanding in neural operator frameworks.
  arXiv  Detail & Related papers  (2024-10-03T01:40:39Z)
• 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)
• Learning to Learn with Generative Models of Neural Network Checkpoints [71.06722933442956]
  We construct a dataset of neural network checkpoints and train a generative model on the parameters. We find that our approach successfully generates parameters for a wide range of loss prompts. We apply our method to different neural network architectures and tasks in supervised and reinforcement learning.
  arXiv  Detail & Related papers  (2022-09-26T17:59:58Z)
• Interpretable Fusion Analytics Framework for fMRI Connectivity: Self-Attention Mechanism and Latent Space Item-Response Model [0.4893345190925178]
  We propose a novel analytical framework that interprets the classification result from deep learning processes. The application of this proposed framework to the four types of cognitive impairment shows that our approach is valid for determining the significant ROI functions.
  arXiv  Detail & Related papers  (2022-07-04T17:01:18Z)
• Dynamically-Scaled Deep Canonical Correlation Analysis [77.34726150561087]
  Canonical Correlation Analysis (CCA) is a method for feature extraction of two views by finding maximally correlated linear projections of them. We introduce a novel dynamic scaling method for training an input-dependent canonical correlation model.
  arXiv  Detail & Related papers  (2022-03-23T12:52:49Z)
• Gone Fishing: Neural Active Learning with Fisher Embeddings [55.08537975896764]
  There is an increasing need for active learning algorithms that are compatible with deep neural networks. This article introduces BAIT, a practical representation of tractable, and high-performing active learning algorithm for neural networks.
  arXiv  Detail & Related papers  (2021-06-17T17:26:31Z)
• Identification of brain states, transitions, and communities using functional MRI [0.5872014229110214]
  We propose a Bayesian model-based characterization of latent brain states and showcase a novel method based on posterior predictive discrepancy. Our results obtained through an analysis of task-fMRI data show appropriate lags between external task demands and change-points between brain states.
  arXiv  Detail & Related papers  (2021-01-26T08:10:00Z)
• An in-depth comparison of methods handling mixed-attribute data for general fuzzy min-max neural network [9.061408029414455]
  We will compare and assess three main methods of handling datasets with mixed features. The experimental results showed that the target and James-Stein are appropriate categorical encoding methods for learning algorithms of GFMM models. The combination of GFMM neural networks and decision trees is a flexible way to enhance the classification performance of GFMM models on datasets with the mixed features.
  arXiv  Detail & Related papers  (2020-09-01T05:12:22Z)
• Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach [144.21892195917758]
  We study estimation in a class of generalized Structural equation models (SEMs) We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using a gradient descent. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.
  arXiv  Detail & Related papers  (2020-07-02T17:55:47Z)
• Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems [83.98774574197613]
  We take one of the simplest inference methods, a truncated max-product Belief propagation, and add what is necessary to make it a proper component of a deep learning model. This BP-Layer can be used as the final or an intermediate block in convolutional neural networks (CNNs) The model is applicable to a range of dense prediction problems, is well-trainable and provides parameter-efficient and robust solutions in stereo, optical flow and semantic segmentation.
  arXiv  Detail & Related papers  (2020-03-13T13:11:35Z)
• A Neural-embedded Choice Model: TasteNet-MNL Modeling Taste Heterogeneity with Flexibility and Interpretability [0.0]
  Discrete choice models (DCMs) require a priori knowledge of the utility functions, especially how tastes vary across individuals. In this paper, we utilize a neural network to learn taste representation. We show that TasteNet-MNL reaches the ground-truth model's predictability and recovers the nonlinear taste functions on synthetic data.
  arXiv  Detail & Related papers  (2020-02-03T18:03:54Z)

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.