
Layerwise Knowledge Extraction from Deep Convolutional Networks
Knowledge extraction is used to convert neural networks into symbolic de...
read it

Neural Networks as Explicit WordBased Rules
Filters of convolutional networks used in computer vision are often visu...
read it

Neural Logic Rule Layers
Despite their great success in recent years, deep neural networks (DNN) ...
read it

NSL: Hybrid Interpretable Learning From Noisy Raw Data
Inductive Logic Programming (ILP) systems learn generalised, interpretab...
read it

Diagnostic Rule Extraction Using Neural Networks
The neural networks have trained on incomplete sets that a doctor could ...
read it

Towards Learning Representations of Binary Executable Files for Security Tasks
Tackling binary analysis problems has traditionally implied manually def...
read it

Logical Learning Through a Hybrid Neural Network with Auxiliary Inputs
The human reasoning process is seldom a oneway process from an input le...
read it
Rule Extraction from Binary Neural Networks with Convolutional Rules for Model Validation
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 highdimensional input data such as images, the individual symbols, i.e. pixels, are not easily interpretable. We introduce the concept of firstorder 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.
READ FULL TEXT
Comments
There are no comments yet.