Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Models

• URL: http://arxiv.org/abs/2305.01939v2
• Date: Fri, 13 Sep 2024 09:22:38 GMT
• Title: Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Models
• Authors: Qihan Ren, Jiayang Gao, Wen Shen, Quanshi Zhang,
• Abstract summary: This study aims to prove the emergence of symbolic concepts (or more precisely, sparse primitive inference patterns) in well-trained deep neural networks (DNNs) We show that inference scores of the DNN on an exponentially large number of randomly masked samples can always be well mimicked by numerical effects of just a few interactions.
• Score: 21.02716340199201
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This study aims to prove the emergence of symbolic concepts (or more precisely, sparse primitive inference patterns) in well-trained deep neural networks (DNNs). Specifically, we prove the following three conditions for the emergence. (i) The high-order derivatives of the network output with respect to the input variables are all zero. (ii) The DNN can be used on occluded samples and when the input sample is less occluded, the DNN will yield higher confidence. (iii) The confidence of the DNN does not significantly degrade on occluded samples. These conditions are quite common, and we prove that under these conditions, the DNN will only encode a relatively small number of sparse interactions between input variables. Moreover, we can consider such interactions as symbolic primitive inference patterns encoded by a DNN, because we show that inference scores of the DNN on an exponentially large number of randomly masked samples can always be well mimicked by numerical effects of just a few interactions.

Related papers

• Randomness of Low-Layer Parameters Determines Confusing Samples in Terms of Interaction Representations of a DNN [67.80700786901016]
  We find that the complexity of interactions encoded by a deep neural network (DNN) can explain its generalization power. We also discover that the confusing samples of a DNN, which are represented by non-generalizable interactions, are determined by its low-layer parameters.
  arXiv  Detail & Related papers  (2025-02-12T18:25:13Z)
• Defining and Extracting generalizable interaction primitives from DNNs [22.79131582164054]
  We develop a new method to extract interactions that are shared by different deep neural networks (DNNs) Experiments show that the extracted interactions can better reflect common knowledge shared by different DNNs.
  arXiv  Detail & Related papers  (2024-01-29T17:21:41Z)
• Harnessing Neuron Stability to Improve DNN Verification [42.65507402735545]
  We present VeriStable, a novel extension of recently proposed DPLL-based constraint DNN verification approach. We evaluate the effectiveness of VeriStable across a range of challenging benchmarks including fully-connected feed networks (FNNs), convolutional neural networks (CNNs) and residual networks (ResNets) Preliminary results show that VeriStable is competitive and outperforms state-of-the-art verification tools, including $alpha$-$beta$-CROWN and MN-BaB, the first and second performers of the VNN-COMP, respectively.
  arXiv  Detail & Related papers  (2024-01-19T23:48:04Z)
• Deep Neural Networks Tend To Extrapolate Predictably [51.303814412294514]
  neural network predictions tend to be unpredictable and overconfident when faced with out-of-distribution (OOD) inputs. We observe that neural network predictions often tend towards a constant value as input data becomes increasingly OOD. We show how one can leverage our insights in practice to enable risk-sensitive decision-making in the presence of OOD inputs.
  arXiv  Detail & Related papers  (2023-10-02T03:25:32Z)
• The #DNN-Verification Problem: Counting Unsafe Inputs for Deep Neural Networks [94.63547069706459]
  #DNN-Verification problem involves counting the number of input configurations of a DNN that result in a violation of a safety property. We propose a novel approach that returns the exact count of violations. We present experimental results on a set of safety-critical benchmarks.
  arXiv  Detail & Related papers  (2023-01-17T18:32:01Z)
• 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)
• Verification-Aided Deep Ensemble Selection [4.290931412096984]
  Deep neural networks (DNNs) have become the technology of choice for realizing a variety of complex tasks. Even an imperceptible perturbation to a correctly classified input can lead to misclassification by a DNN. This paper devises a methodology for identifying ensemble compositions that are less prone to simultaneous errors.
  arXiv  Detail & Related papers  (2022-02-08T14:36:29Z)
• A Survey on Assessing the Generalization Envelope of Deep Neural Networks: Predictive Uncertainty, Out-of-distribution and Adversarial Samples [77.99182201815763]
  Deep Neural Networks (DNNs) achieve state-of-the-art performance on numerous applications. It is difficult to tell beforehand if a DNN receiving an input will deliver the correct output since their decision criteria are usually nontransparent. This survey connects the three fields within the larger framework of investigating the generalization performance of machine learning methods and in particular DNNs.
  arXiv  Detail & Related papers  (2020-08-21T09:12:52Z)
• GraN: An Efficient Gradient-Norm Based Detector for Adversarial and Misclassified Examples [77.99182201815763]
  Deep neural networks (DNNs) are vulnerable to adversarial examples and other data perturbations. GraN is a time- and parameter-efficient method that is easily adaptable to any DNN. GraN achieves state-of-the-art performance on numerous problem set-ups.
  arXiv  Detail & Related papers  (2020-04-20T10:09:27Z)
• Interval Neural Networks: Uncertainty Scores [11.74565957328407]
  We propose a fast, non-Bayesian method for producing uncertainty scores in the output of pre-trained deep neural networks (DNNs) This interval neural network (INN) has interval valued parameters and propagates its input using interval arithmetic. In numerical experiments on an image reconstruction task, we demonstrate the practical utility of INNs as a proxy for the prediction error.
  arXiv  Detail & Related papers  (2020-03-25T18:03:51Z)

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.