A neural network for fast inferencing on a fuzzy knowledge base

2003 ◽  
Author(s):  
K.S. Kumar ◽  
M. Sparancia ◽  
A. Unnikrishnan
Keyword(s):  
Neural Network ◽  
Knowledge Base ◽  
Fuzzy Knowledge

scholarly journals Short-Term Fuzzy Load Forecasting Model Using Genetic–Fuzzy and Ant Colony–Fuzzy Knowledge Base Optimization

2018 ◽  
Vol 8 (6) ◽  
pp. 864 ◽  
Author(s):  
Murat Luy ◽  
Volkan Ates ◽  
Necaattin Barisci ◽  
Huseyin Polat ◽  
Ertugrul Cam
Keyword(s):  
Knowledge Base ◽  
Load Forecasting ◽  
Ant Colony ◽  
Forecasting Model ◽  
Short Term ◽  
Fuzzy Knowledge

A convolutional neural network-based model for knowledge base completion and its application to search personalization

Semantic Web ◽  
2019 ◽  
Vol 10 (5) ◽  
pp. 947-960 ◽  
Author(s):  
Dai Quoc Nguyen ◽  
Dat Quoc Nguyen ◽  
Tu Dinh Nguyen ◽  
Dinh Phung
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Knowledge Base

scholarly journals Knowledge Base Completion with Out-of-Knowledge-Base Entities: A Graph Neural Network Approach

2018 ◽  
Vol 33 (2) ◽  
pp. F-H72_1-10 ◽  
Author(s):  
Takuo Hamaguchi ◽  
Hidekazu Oiwa ◽  
Masashi Shimbo ◽  
Yuji Matsumoto
Keyword(s):  
Neural Network ◽  
Knowledge Base ◽  
Network Approach ◽  
Neural Network Approach

Web Intelligence

Big Data ◽  
2016 ◽  
pp. 711-733 ◽  
Author(s):  
Jafreezal Jaafar ◽  
Kamaluddeen Usman Danyaro ◽  
M. S. Liew
Keyword(s):  
Big Data ◽  
Knowledge Base ◽  
Data Model ◽  
Performance Comparison ◽  
Web Ontology Language ◽  
Web Intelligence ◽  
Knowledge Based ◽  
Ontology Language ◽  
And Performance ◽  
Fuzzy Knowledge

This chapter discusses about the veracity of data. The veracity issue is the challenge of imprecision in big data due to influx of data from diverse sources. To overcome this problem, this chapter proposes a fuzzy knowledge-based framework that will enhance the accessibility of Web data and solve the inconsistency in data model. D2RQ, protégé, and fuzzy Web Ontology Language applications were used for configuration and performance. The chapter also provides the completeness fuzzy knowledge-based algorithm, which was used to determine the robustness and adaptability of the knowledge base. The result shows that the D2RQ is more scalable with respect to performance comparison. Finally, the conclusion and future lines of the research were provided.

Cognition of a Robotic Manipulator Using the Q-Learning Based Situation-Operator Model

2018 ◽  
Vol 11 (1) ◽  
pp. 146-157 ◽  
Author(s):  
Akash Dutt Dubey ◽  
Ravi Bhushan Mishra
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Path Planning ◽  
Mobile Robot ◽  
Knowledge Base ◽  
Operator Model ◽  
Q Learning ◽  
Sensory Inputs ◽  
Learning Module ◽  
Som Model

In this article, we have applied cognition on robot using Q-learning based situation operator model. The situation operator model takes the initial situation of the mobile robot and applies a set of operators in order to move the robot to the destination. The initial situation of the mobile robot is defined by a set of characteristics inferred by the sensor inputs. The Situation-Operator Model (SOM) model comprises of a planning and learning module which uses certain heuristics for learning through the mobile robot and a knowledge base which stored the experiences of the mobile robot. The control and learning of the robot is done using q-learning. A camera sensor and an ultrasonic sensor were used as the sensory inputs for the mobile robot. These sensory inputs are used to define the initial situation, which is then used in the learning module to apply the valid operator. The results obtained by the proposed method were compared to the result obtained by Reinforcement-Based Artificial Neural Network for path planning.

Sign in / Sign up

Export Citation Format

Share Document