Rule Extraction from Binary Neural Networks with Convolutional Rules for Model Validation

• URL: http://arxiv.org/abs/2012.08459v1
• Date: Tue, 15 Dec 2020 17:55:53 GMT
• Title: Rule Extraction from Binary Neural Networks with Convolutional Rules for Model Validation
• Authors: Sophie Burkhardt, Jannis Brugger, Nicolas Wagner, Zahra Ahmadi, Kristian Kersting and Stefan Kramer
• Abstract summary: We introduce the concept of first-order convolutional rules, which are logical rules that can be extracted using a convolutional neural network (CNN) Our approach is based on rule extraction from binary neural networks with local search. Our experiments show that the proposed approach is able to model the functionality of the neural network while at the same time producing interpretable logical rules.
• Score: 16.956140135868733
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Most deep neural networks are considered to be black boxes, meaning their output is hard to interpret. In contrast, logical expressions are considered to be more comprehensible since they use symbols that are semantically close to natural language instead of distributed representations. However, for high-dimensional input data such as images, the individual symbols, i.e. pixels, are not easily interpretable. We introduce the concept of first-order convolutional rules, which are logical rules that can be extracted using a convolutional neural network (CNN), and whose complexity depends on the size of the convolutional filter and not on the dimensionality of the input. Our approach is based on rule extraction from binary neural networks with stochastic local search. We show how to extract rules that are not necessarily short, but characteristic of the input, and easy to visualize. Our experiments show that the proposed approach is able to model the functionality of the neural network while at the same time producing interpretable logical rules.

Related papers

• Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations [54.17275171325324]
  We present a counterexample to the Linear Representation Hypothesis (LRH) When trained to repeat an input token sequence, neural networks learn to represent the token at each position with a particular order of magnitude, rather than a direction. These findings strongly indicate that interpretability research should not be confined to the LRH.
  arXiv  Detail & Related papers  (2024-08-20T15:04:37Z)
• Neural networks trained with SGD learn distributions of increasing complexity [78.30235086565388]
  We show that neural networks trained using gradient descent initially classify their inputs using lower-order input statistics. We then exploit higher-order statistics only later during training. We discuss the relation of DSB to other simplicity biases and consider its implications for the principle of universality in learning.
  arXiv  Detail & Related papers  (2022-11-21T15:27:22Z)
• NN2Rules: Extracting Rule List from Neural Networks [0.913755431537592]
  NN2Rules is a decompositional approach to rule extraction, i.e., it extracts a set of decision rules from the parameters of the trained neural network model. We show that the decision rules extracted have the same prediction as the neural network on any input presented to it, and hence the same accuracy.
  arXiv  Detail & Related papers  (2022-07-04T09:19:47Z)
• Concept Embeddings for Fuzzy Logic Verification of Deep Neural Networks in Perception Tasks [1.2246649738388387]
  We present a simple, yet effective, approach to verify whether a trained convolutional neural network (CNN) respects specified symbolic background knowledge. The knowledge may consist of any fuzzy predicate logic rules. We show that this approach benefits from fuzziness and calibrating the concept outputs.
  arXiv  Detail & Related papers  (2022-01-03T10:35:47Z)
• 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)
• The Separation Capacity of Random Neural Networks [78.25060223808936]
  We show that a sufficiently large two-layer ReLU-network with standard Gaussian weights and uniformly distributed biases can solve this problem with high probability. We quantify the relevant structure of the data in terms of a novel notion of mutual complexity.
  arXiv  Detail & Related papers  (2021-07-31T10:25:26Z)
• Artificial Neural Networks generated by Low Discrepancy Sequences [59.51653996175648]
  We generate artificial neural networks as random walks on a dense network graph. Such networks can be trained sparse from scratch, avoiding the expensive procedure of training a dense network and compressing it afterwards. We demonstrate that the artificial neural networks generated by low discrepancy sequences can achieve an accuracy within reach of their dense counterparts at a much lower computational complexity.
  arXiv  Detail & Related papers  (2021-03-05T08:45:43Z)
• Towards Understanding Hierarchical Learning: Benefits of Neural Representations [160.33479656108926]
  In this work, we demonstrate that intermediate neural representations add more flexibility to neural networks. We show that neural representation can achieve improved sample complexities compared with the raw input. Our results characterize when neural representations are beneficial, and may provide a new perspective on why depth is important in deep learning.
  arXiv  Detail & Related papers  (2020-06-24T02:44:54Z)
• Deep Networks as Logical Circuits: Generalization and Interpretation [10.223907995092835]
  We present a hierarchical decomposition of the Deep Neural Networks (DNNs) discrete classification map into logical (AND/OR) combinations of intermediate (True/False) classifiers of the input. We show that the learned, internal, logical computations correspond to semantically meaningful categories that allow DNN descriptions in plain English.
  arXiv  Detail & Related papers  (2020-03-25T20:39:53Z)
• Layerwise Knowledge Extraction from Deep Convolutional Networks [0.9137554315375922]
  We propose a novel layerwise knowledge extraction method using M-of-N rules. We show that this approach produces rules close to an optimal complexity-error tradeoff. We also find that the softmax layer in Convolutional Neural Networks and Autoencoders is highly explainable by rule extraction.
  arXiv  Detail & Related papers  (2020-03-19T19:46:45Z)

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.