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

by   Sophie Burkhardt, et al.

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.


page 10

page 12

page 13

page 17


Layerwise Knowledge Extraction from Deep Convolutional Networks

Knowledge extraction is used to convert neural networks into symbolic de...

Neural Networks as Explicit Word-Based Rules

Filters of convolutional networks used in computer vision are often visu...

Neural Logic Rule Layers

Despite their great success in recent years, deep neural networks (DNN) ...

Diagnostic Rule Extraction Using Neural Networks

The neural networks have trained on incomplete sets that a doctor could ...

NSL: Hybrid Interpretable Learning From Noisy Raw Data

Inductive Logic Programming (ILP) systems learn generalised, interpretab...

Logical Learning Through a Hybrid Neural Network with Auxiliary Inputs

The human reasoning process is seldom a one-way process from an input le...

Towards Learning Representations of Binary Executable Files for Security Tasks

Tackling binary analysis problems has traditionally implied manually def...