Generation of Explicit Knowledge from Empirical Data through Pruning of Trainable Neural Networks

by   Alexander N. Gorban, et al.

This paper presents a generalized technology of extraction of explicit knowledge from data. The main ideas are 1) maximal reduction of network complexity (not only removal of neurons or synapses, but removal all the unnecessary elements and signals and reduction of the complexity of elements), 2) using of adjustable and flexible pruning process (the pruning sequence shouldn't be predetermined - the user should have a possibility to prune network on his own way in order to achieve a desired network structure for the purpose of extraction of rules of desired type and form), and 3) extraction of rules not in predetermined but any desired form. Some considerations and notes about network architecture and training process and applicability of currently developed pruning techniques and rule extraction algorithms are discussed. This technology, being developed by us for more than 10 years, allowed us to create dozens of knowledge-based expert systems. In this paper we present a generalized three-step technology of extraction of explicit knowledge from empirical data.



There are no comments yet.



Neuron Pruning for Compressing Deep Networks using Maxout Architectures

This paper presents an efficient and robust approach for reducing the si...

Prune Your Model Before Distill It

Unstructured pruning reduces a significant amount of weights of neural n...

Data-dependent Pruning to find the Winning Lottery Ticket

The Lottery Ticket Hypothesis postulates that a freshly initialized neur...

Prunnig Algorithm of Generation a Minimal Set of Rule Reducts Based on Rough Set Theory

In this paper it is considered rule reduct generation problem, based on ...

Methods for Pruning Deep Neural Networks

This paper presents a survey of methods for pruning deep neural networks...

Eclectic Extraction of Propositional Rules from Neural Networks

Artificial Neural Network is among the most popular algorithm for superv...

Convolutional Network Fabric Pruning With Label Noise

This paper presents an iterative pruning strategy for Convolutional Netw...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.