Deepak Khemani

The objective of this study is to explore the possibility of capturing the reasoning process used in bidding a hand in a bridge game by an artificial neural network. We show that a multilayer feedforward neural network can be trained to learn to make an opening bid with a new hand. The game of bridge, like many other games used in artificial intelligence, can easily be represented in a machine. But, unlike most games used in artificial intelligence, bridge uses subtle reasoning over and above the agreed conventional system, to make a bid from the pattern of a given hand. Although it is difficult for a player to spell out the precise reasoning process he uses, we find that a neural network can indeed capture it. We demonstrate the results for the case of one-level opening bids, and discuss the need for a hierarchical architecture to deal with bids at all levels.

The phrase artificial intelligence has become common in our current day discourse. Fuelled by successes in machine learning, and applications interacting with us in speech and natural language, many commentators have made a leap of faith that behind these successes is a thinking machine, and this has even stoked fears of machines overcoming humankind. In this two-part article, we look at how close we are to the original quest for creating “machines who think”. In the first part, we trace the evolution of mechanical computers and also the notion of the mind up to the era before digital computers appeared on the horizon.

This paper presents a survey of Simultaneous Localization And Mapping (SLAM) algorithms for unmanned ground robots. SLAM is the process of creating a map of the environment, sometimes unknown a priori, while at the same time localizing the robot in the same map. The map could be one of different types i.e.metrical, topological, hybrid or semantic. In this paper, the classification of algorithms is done in three classes: (i) Metric map generating approaches, (ii) Qualitative map generating approaches, and (iii) Hybrid map generating approaches. SLAM algorithms for both static and dynamic environments have been surveyed. The algorithms in each class are further divided based on the techniques used. The survey in this paper presents the current state-of-the-art methods, including important landmark works reported in the literature.

Clusters of text documents output by clustering algorithms are often hard to interpret. We describe motivating real-world scenarios that necessitate reconfigurability and high interpretability of clusters and outline the problem of generating clusterings with interpretable and reconfigurable cluster models. We develop two clustering algorithms toward the outlined goal of building interpretable and reconfigurable cluster models. They generate clusters with associated rules that are composed of conditions on word occurrences or nonoccurrences. The proposed approaches vary in the complexity of the format of the rules; RGC employs disjunctions and conjunctions in rule generation whereas RGC-D rules are simple disjunctions of conditions signifying presence of various words. In both the cases, each cluster is comprised of precisely the set of documents that satisfy the corresponding rule. Rules of the latter kind are easy to interpret, whereas the former leads to more accurate clustering. We show that our approaches outperform the unsupervised decision tree approach for rule-generating clustering and also an approach we provide for generating interpretable models for general clusterings, both by significant margins. We empirically show that the purity and f-measure losses to achieve interpretability can be as little as 3 and 5%, respectively using the algorithms presented herein. © 2011 Springer-Verlag London Limited.

For more than 25 years Ford Motor Company has been utilizing an AI-based system to manage process planning for vehicle assembly at its assembly plants around the world. The scope of the AI system, known originally as the Direct Labor Management System and now as the Global Study Process Allocation System (GSPAS), has increased over the years to include additional functionality on ergonomics and powertrain assembly (engines and transmission plants). The knowledge about Ford's manufacturing processes is contained in an ontology originally developed using the KL-ONE representation language and methodology. To preserve the viability of the GSPAS ontology and to make it easily usable for other applications within Ford, we needed to reengineer and convert the KL-ONE ontology into a semantic web OWL/RDF format. In this article, we will discuss the process by which we reengineered the existing GSPAS KLONE ontology and deployed semantic web technology in our application.

In the first week of the year 2020, we got the news that AI now outperforms doctors in detecting breast cancer. This is in line with a continuous stream of news coming from the world of diagnosis and has lent credence to the sentiment that AI is poised to overcome humankind. However, some perceptive observers have commented that recent advances are largely due to the massive increase in both availability of data and computing power. Moreover, it is only a narrow task of classification that has led the news blitz. Classification can be thought of as a stimulus-response process. Human intelligence is much broader. In particular, humans often display a stimulus-deliberation-response cycle. There is much that goes on in the “thinking” phase that was the original aim of AI before the data and speed started dominating applications. The second of the two-part article on AI traces the evolution in the field since the Dartmouth conference, and takes stock of where we are on the road to thinking machines.

Process control systems usually generate a system activity log or trace. Normal behavior results in normal patterns in the trace. We model the normal trace patterns using a context free grammar and develop a technique for automatic qualitative diagnosis, based on grammar perturbation, to recognize deviations from the normal trace patterns.

India is a multilingual and multicultural country that came together less than a century ago. The populace spans wide extremes of wealth and education. The artificial intelligence community, which gained in strength in the 1980s, has had a major focus on research directed toward societal goals of bridging the linguistic and educational divide, and delivers the fruits of information technology to all people. In this article we look at a brief history followed by two examples of research aimed at crossing the language barriers. Copyright © 2012, Association for the Advancement of Artificial Intelligence. All rights reserved.

In this paper, an evolutionary programming-based clustering algorithm is proposed. The algorithm effectively groups a given set of data into an optimum number of clusters. The proposed method is applicable for clustering tasks where clusters are crisp and spherical. This algorithm determines the number of clusters and the cluster centers in such a way that locally optimal solutions are avoided. The result of the algorithm does not depend critically on the choice of the initial cluster centers. © 1997 Published by Elsevier Science B.V.

The task of planning in a dynamic and an uncertain domain is considerably more challenging than in domains traditionally adopted by ai planning methods. Planning in real situations has to be a knowledge intensive process, particularly since it is not easy to predict all the effects of one's actions. Contract bridge offers a domain in which many of the issues involved in real world problems can be addressed without having to make simplifications in representation. Planning in the game of bridge takes us away from the traditional search-based methods (like the alpha-beta procedure), which are applicable in complete-information games like chess. In this paper we look at how knowledge can be structured to plan for declarer play in bridge. This involves deploying known move combinations, triggered by patterns which are abstracted out of the input, and then assembling the structures into a workable plan. The results demonstrate the viability of the proposed concepts. © 1994 the Indian Academy of Sciences.