Purvag Patel

An inference engine toolkit for computing with words

Computing with Words is an emerging paradigm in knowledge representation and information processing. It provides a mathematical model to represent the meaning of imprecise words and phrases in natural language and introduces advanced techniques to perform reasoning on inexact knowledge. Since its introduction, there have been many studies on computing with words but mostly from the theoretical point of view and the paradigm still lacks sufficient support from the software side. This paper is an attempt to fill this gap by presenting an enhanced inference engine toolkit for supporting computing with words. The scope of the presented toolkit, as opposed to many available fuzzy logic tools, goes beyond simple fuzzy-if-then rules and performs a chain of inferences on complex fuzzy propositions containing fuzzy arithmetics, fuzzy quantifiers, and fuzzy probabilities. The toolkit may be appealing to researchers, practitioners, and educators in knowledge based applications and soft computing as it implements a powerful declarative language which allows users to express their knowledge in a more natural and convenient way and performs a chain of reasoning on imprecise propositions.

Designing BOTs with BDI agents

In modern computer games, ‘bots’ - Intelligent realistic agents play a prominent role in success of a game in market. Typically, bots are modeled using finite-state machine and then programmed via simple conditional statements which are hard-coded in bots logic. Since these bots have become quite predictable to an experienced games player, she might lose her interest in game. We present a model of bots using BDI agents, which will show more human-like behavior, more believable and will provide more realistic feel to the game. These bots will use the inputs from actual game players to specify her Beliefs, Desires, and Intentions while game playing.

CWJess: Implementation of an expert system shell for Computing with Words

Computing with Words (CW) is an emerging paradigm in knowledge representation and information processing. It provides a mathematical model to represent the meaning of imprecise words and phrases in natural language, and to perform reasoning on perceptual knowledge. This paper describes a preliminary extension to Jess, CWJess, which allows reasoning in the framework of Computing with Words (CW). The resulting inference shell significantly enhances the expressiveness and reasoning power of fuzzy expert systems and provides a Java API which allows users to express various types of fuzzy concepts, including: fuzzy graphs, fuzzy relations, fuzzy arithmetic expression, and fuzzy quantified propositions. CWJess is fully integrated with jess and utilizes jess Rete network to perform a chain of reasoning on fuzzy propositions.

An API for generalized constraint language based expert system

Human possess inherent capabilities to store, processes and reason on imprecise information in the form of perceptions in natural language. Generalized theory of uncertainty (GTU) is a methodology for reasoning, representing, and performing computations on such imprecise information. Generalized constraint, the basic data structure in GTU, is used to represent and propagate information. There is no previous attempt to implement this theoretical methodology. This paper reports the implementation of a Java API toolkit for generalized constraint language (GCL) that can be easily expanded for practical applications of GTU in the form of an expert system. Toolkit allows users to express various types of GTU concepts, such as generalized constraint, fuzzy graphs, fuzzy relations, and fuzzy arithmetic expression. Toolkit is fully integrated with Jess (Java Expert System Shell) and utilizes Jess Rete network for deductions on generalized constraints.

An evaluation of retranslation methods in computing with words

To represent output fuzzy values of a computing with words (CW) system in natural language, a retranslation unit is required. In this work, retranslation methods applicable to a CW system are explored. Several methods that employ similarity measures of fuzzy sets, linguistic modifiers, or linguistic quantifiers have been applied to three real-world case studies. Performances of the applied methods have been evaluated through degree of validity, and comparison of characteristics of fuzzy sets such as fuzziness and specificity. Results show that invalid linguistic terms might be used in the retranslation process which also cause incomprehensible phrases in natural language.

Towards retranslation of fuzzy values in computing with words

Any conceptual computer or computing with words (CW) system is expected to represent its results with a reasonable output, such as a sentence in natural language. A CW system is required to translate the fuzzy values provided as its result into words. This paper explores different similarity measures as well as linguistic approximation methods for generating natural language sentences for CW systems. Methods in both approaches are evaluated through various measures such as fuzziness, specificity, validity, and sigma-count. Evaluation results suggest certain linguistic methods may result in complex and incomprehensible phrases in natural language. They might even include an invalid linguistic term in their linguistic approximation. On the other hand, methods based on similarity measures may result in simpler and more comprehensible linguistic terms but might not be able to select a perfect match.

Applied Z-numbers

Z-number is an emerging paradigm that has been utilized in computing with words among others. The concept of a Z-number is intended to provide a basis for computation with numbers that deal with reliability and likelihood. Z-numbers are confluence between the two most prominent approaches to uncertainty, probability and possibility, which allow computations on complex statements. computations on Z-numbers require solving a complex optimization problem over the space of all possible probability distribution which leads in to its slow adoption to computing with words machinery. This paper seeks to provide an applied model of Z-numbers based on certain realistic assumptions regarding the probability distributions. An algorithm and example is presented to demonstrate the applicability of the model.

Bootstrapping learning from abstract models in games

Computer gaming environments are real time, dynamic, and complex, with incomplete knowledge of the world. Agents in such environments require detailed models of the world if they are to learn effective policies. Machine learning techniques such as reinforcement learning can become intractably large, detailed world models. In this paper we tackle the well-known problem of low convergence speed in reinforcement learning for the detailed model of the world, specifically for video games. We propose first training the agents with an abstract model of the world and then using the resulting policy to initialise the system prior to training the agent with the detailed model of the world. This paper reports on results from applying the proposed technique to the classic arcade game Asteroids. Our experiments show that an agent can quickly learn a policy with the abstract model, and that when this policys learned values are used to initialise the detailed model, learning with the detailed model improves the rate of convergence.