Rule extraction from neural networks (NNs) solves two fundamental problems: it gives insight into the logic behind the network and in many cases, it improves the network's ability to generalize the acquired knowledge. This paper presents a novel eclectic approach to rule extraction from NNs, named LOcal Rule Extraction (LORE), suited for multilayer perceptron networks with discrete (logical or categorical) inputs. The extracted rules mimic network behavior on the training set and relax this condition on the remaining input space. First, a multilayer perceptron network is trained under standard regime. It is then transformed into an equivalent form, returning the same numerical result as the original network, yet being able to produce rules generalizing the network output for cases similar to a given input. The partial rules extracted for every training set sample are then merged to form a decision diagram (DD) from which logic rules can be extracted. A rule format explicitly separating subsets of inputs for which an answer is known from those with an undetermined answer is presented. A special data structure, the decision diagram, allowing efficient partial rule merging is introduced. With regard to rules' complexity and generalization abilities, LORE gives results comparable to those reported previously. An algorithm transforming DDs into interpretable boolean expressions is described. Experimental running times of rule extraction are proportional to the network's training time.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE : Extracting 3D Layout From a Single Image Using Global Image Structures - 2015 ABSTRACT: Extracting the pixel-level 3D layout from a single image is important for various applications, such as object localization,
PROJECT TITLE : Extracting Salient Brain Patterns For Imaging Based Classification Of Neurodegenerative Diseases - 2014 ABSTRACT: Neurodegenerative diseases comprise a wide range of mental symptoms whose evolution is not directly
PROJECT TITLE : Design of a Network of Digital Sensor Macros for Extracting Power Supply Noise Profile in SoCs - 2016 ABSTRACT: Increased practical density with shrinking technology may lead to escalating power supply noise
PROJECT TITLE :Proof-of-Principle Experiment on High-Power Gyrotron Traveling-Wave Tube With a Microwave System for Driving and Extracting Power Through One WindowABSTRACT:A previously proposed technique, which allows feeding
PROJECT TITLE :Extracting Cross-Ontology Weighted Association Rules from Gene Ontology AnnotationsABSTRACT:Gene Ontology (GO) may be a structured repository of concepts (GO Terms) that are associated to at least one or additional

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry