Neuron Activation-based Computation of Logical Explanations for Deep Neural Networks

• URL: http://arxiv.org/abs/2609.14099v1
• Date: Sat, 12 Sep 2026 18:50:37 GMT
• Title: Neuron Activation-based Computation of Logical Explanations for Deep Neural Networks
• Abstract summary: This paper introduces a flexible symbolic framework for an efficient, guided computation of explanations of the NN behavior.<n>We show that our method yields explanations that are not restricted in shape.<n> Notably, our approach enables logical explanation of deep networks not amenable to prior logic-based methods.
• Score: 2.753173444623078
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Formal explainability of classifying neural networks (NNs) is an active area of research, providing explanations with provable guarantees of the classification within continuous regions of the input feature space. However, the existing techniques are either limited to individual input features without guarantees on their relations or the provided solutions fail to scale to deep architectures. This paper addresses these issues by introducing a flexible symbolic framework for an efficient, guided computation of explanations of the NN behavior, parametrized by the activations of internal neurons, and using logical engines such as SMT solvers. Unlike prior methods that rely on specialized NN verifiers, our method yields explanations that are not restricted in shape. Our algorithm is implementable on top of a general-purpose logical solver, isolating the NN-specific encoding from the algorithmic framework. We experimented with a wide range of benchmarks from the domains of image recognition and medicine, illustrating the advantages of the new method, particularly in computational efficiency. Notably, our approach enables logical explanation of deep networks not amenable to prior logic-based methods.

Related papers

• Dynamics and Representation Structure of Local Approximations to Gradient-Based Learning in Linear Recurrent Neural Networks [56.42974363744522]
  We study the learning dynamics of random feedback local online (RFLO) and truncated backpropagation through time (tBPTT)<n>Our work provides analytical insight into how locality constraints shape learning dynamics, with implications for neuroscientific models of learning and alternative optimization approaches for RNNs.
  arXiv  Detail & Related papers  (2026-05-29T18:19:45Z)
• Slice and Explain: Logic-Based Explanations for Neural Networks through Domain Slicing [3.847524185858632]
  This paper proposes an approach leveraging domain slicing to facilitate explanation generation for NNs.<n>By reducing the complexity of logical constraints through slicing, we decrease explanation time by up to 40% less time.
  arXiv  Detail & Related papers  (2026-02-25T17:01:52Z)
• The Finite Element Neural Network Method: One Dimensional Study [0.0]
  This research introduces the finite element neural network method (FENNM) within the framework of the Petrov-Galerkin method.<n>FENNM uses convolution operations to approximate the weighted residual of the differential equations.<n>This enables the integration of forcing terms and natural boundary conditions into the loss function similar to conventional finite element method (FEM) solvers.
  arXiv  Detail & Related papers  (2025-01-21T21:39:56Z)
• A simple algorithm for output range analysis for deep neural networks [0.0]
  This paper presents a novel approach for the output range estimation problem in Deep Neural Networks (DNNs) by integrating a Simulated Annealing (SA) algorithm.<n>The method effectively addresses the challenges by the lack of geometric information and non-linearity inherent inResNets.
  arXiv  Detail & Related papers  (2024-07-02T22:47:40Z)
• N-Adaptive Ritz Method: A Neural Network Enriched Partition of Unity for Boundary Value Problems [1.2200609701777907]
  This work introduces a novel neural network-enriched Partition of Unity (NN-PU) approach for solving boundary value problems via artificial neural networks. The NN enrichment is constructed by combining pre-trained feature-encoded NN blocks with an untrained NN block. The proposed method offers accurate solutions while notably reducing the computational cost compared to the conventional adaptive refinement in the mesh-based methods.
  arXiv  Detail & Related papers  (2024-01-16T18:11:14Z)
• Manipulating Feature Visualizations with Gradient Slingshots [53.94925202421929]
  Feature Visualization (FV) is a widely used technique for interpreting the concepts learned by Deep Neural Networks (DNNs)<n>We introduce a novel method, Gradient Slingshots, that enables manipulation of FV without modifying the model architecture or significantly degrading its performance.
  arXiv  Detail & Related papers  (2024-01-11T18:57:17Z)
• Comparative Analysis of Interval Reachability for Robust Implicit and Feedforward Neural Networks [64.23331120621118]
  We use interval reachability analysis to obtain robustness guarantees for implicit neural networks (INNs) INNs are a class of implicit learning models that use implicit equations as layers. We show that our approach performs at least as well as, and generally better than, applying state-of-the-art interval bound propagation methods to INNs.
  arXiv  Detail & Related papers  (2022-04-01T03:31:27Z)
• Neuro-Symbolic Inductive Logic Programming with Logical Neural Networks [65.23508422635862]
  We propose learning rules with the recently proposed logical neural networks (LNN) Compared to others, LNNs offer strong connection to classical Boolean logic. Our experiments on standard benchmarking tasks confirm that LNN rules are highly interpretable.
  arXiv  Detail & Related papers  (2021-12-06T19:38:30Z)
• Reinforcement Learning with External Knowledge by using Logical Neural Networks [67.46162586940905]
  A recent neuro-symbolic framework called the Logical Neural Networks (LNNs) can simultaneously provide key-properties of both neural networks and symbolic logic. We propose an integrated method that enables model-free reinforcement learning from external knowledge sources.
  arXiv  Detail & Related papers  (2021-03-03T12:34:59Z)
• 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)
• Parallelization Techniques for Verifying Neural Networks [52.917845265248744]
  We introduce an algorithm based on the verification problem in an iterative manner and explore two partitioning strategies. We also introduce a highly parallelizable pre-processing algorithm that uses the neuron activation phases to simplify the neural network verification problems.
  arXiv  Detail & Related papers  (2020-04-17T20:21:47Z)

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.