Kankanahalli Srinivas

Encoding Techniques for Complex Information Structures in Connectionist Systems

Two general information-encoding techniques called ‘relative-position encoding’ and ‘pattern-similarity association’ are presented. They are claimed to be a convenient basis for the connectionist implementation of complex, short-term information processing of the sort needed in commonsense reasoning, semantic/pragmatic interpretation of natural language utterances, and other types of high-level cognitive processing. The relationships of the techniques to other connectionist information-structuring methods, and also to methods used in computers, are discussed in detail. The rich interrelationships of these other connectionist and computer methods are also clarified. We detail the particular, simple forms that the relative-position encoding and pattern-similarity association techniques take in our own connectionist system, called Conposit, in order to clarify some issues and to provide evidence that the techniques are indeed useful in practice.

Overcoming rule-based rigidity and connectionist limitations through massively-parallel case-based reasoning

Abstract Symbol manipulation as used in traditional Artificial Intelligence has been criticized by neural net researchers for being excessively inflexible and sequential. On the other hand, the application of neural net techniques to the types of high-level cognitive processing studied in traditional artificial intelligence presents major problems as well. We claim that a promising way out of this impasse is to build neural net models that accomplish massively parallel case-based reasoning. Case-based reasoning, which has received much attention recently, is essentially the same as analogy-based reasoning, and avoids many of the problems leveled at traditional artificial intelligence. Further problems are avoided by doing many strands of case-based reasoning in parallel, and by implementing the whole system as a neural net. In addition, such a system provides an approach to some aspects of the problems of noise, uncertainty and novelty in reasoning systems. We are accordingly modifying our current neural net system (Conposit), which performs standard rule-based reasoning, into a massively parallel case-based reasoning version.

Temporal winner-take-all networks: a time-based mechanism for fast selection in neural networks

Winner-take-all (WTA) networks frequently appear in neural network models. They are primarily used for decision making and selection. As an alternative to the conventional activation-based winner-take-all mechanisms (AWTA), we present a time-based temporal-winner-take-all mechanism with O(n) space complexity and roughly O(log n) time complexity. The mechanism exploits systematic and stochastic differences between time delays within different units and connections. The TWTA and the AWTA networks are shown to be logically equivalent, but the TWTA mechanism may be more suitable than the latter for various selection tasks, especially the selection of an arbitrary unit from a set (e.g., as in unit recruitment). TWTA avoids various problems with conventional WTA, notably the difficulty of making it converge rapidly over a large range of conditions. Here we report a probabilistic analysis of the TWTA mechanism along with experimental data obtained from numerous massively parallel simulations of the TWTA mechanism on the connection machine.

Infrastructure support for multimedia communications: a survey

The survey provides a concise review of the current progress achieved in the field of multimedia computing. It covers properties of multimedia, switching and compression standards, communication support, synchronization support, operating system support, and discussion on possible future research.<<ETX>>

A parallel algorithm for computing polygon set operations

We present a parallel algorithm for performing Boolean set operations on generalized polygons that have holes in them. The intersection algorithm has a processor complexity of O(m/sup 2/n/sup 2/) processors and a time complexity of O(max(2logm, log/sup 2/n)), where m is the maximum number of vertices in any loop of a polygon, and n is the maximum number of loops per polygon. The union and difference algorithms have a processor complexity of O(m/sup 2/n/sup 2/) and time complexity of O(logm) and O(2logm, logn) respectively. The algorithm is based on the EREW PRAM model. The algorithm tries to minimize the intersection point computations by intersecting only a subset of loops of the polygons based on of their topological relationships.<<ETX>>

Detection, Isolation and Characterization of Principal Synthetic Route Indicative Impurity in Lansoprazole

An unknown impurity in lansoprazole (2-[[[3-methyl-4-(2, 2, 2-trifluoroethoxy)-2-pyridyl] methyl] sulfinyl] benzimidazole) was detected by HPLC and was identified as des-(trifluoroethoxy) lansoprazole, an principal synthetic route indicative impurity of lansoprazole. Lansoprazole was subjected to different ICH prescribed stress conditions like hydrolysis, oxidation, photolysis and thermal degradation conditions to enrich the impurity. The impurity was enriched by using acid catalytic degradation, isolated by using preparative HPLC and characterized (FTIR, MS and NMR). Limit of Detection (LOD) and Limit of Quantification (LOQ) are found to be 0.014% and 0.035% respectively.

Reducing disk power consumption in a portable computer

The problem of minimizing disk power consumption in portable personal computers is studied. Two online algorithms for determining when to stop spinning a disk are presented and analyzed using competitive analysis techniques.

Functional specifications for collaboration services

Describes an attempt at specifying a generic and reusable set of services for computer-supported collaboration among teams engaged in any collaborative process within a distributed organization or group of organizations. The services are cataloged under the headings: information management, group communications, group management, process management, and infrastructure support.<<ETX>>

Quantification without variables in connectionism

Connectionist attention to variables has been too restricted in two ways. First, it has not exploited certain ways of doing without variables in the symbolic arena. One variable-avoidance method, that of logical combinators, is particularly well established there. Secondly, the attention has been largely restricted to variables in long-term rules embodied in connection weight patterns. However, short-lived bodies of information, such as sentence interpretations or inference products, may involve quantification. Therefore short-lived activation patterns may need to achieve the effect of variables. The paper is mainly a theoretical analysis of some benefits and drawbacks of using logical combinators to avoid variables in short-lived connectionist encodings without loss of expressive power. The paper also includes a brief survey of some possible methods for avoiding variables other than by using combinators.

A collaborative environment for independent verification and validation of software

The collaborative approach to product development is becoming increasingly recognized as a key to improve the productivity of the participating team members. However, in practice, its realization is hindered by the lack of computing environments to support collaborative work. The set of basic transactions needed in a collaborative setting consists of a variety of activities: look up, communicate, compute, decide, negotiate, and archive. We discuss a generic architecture for a collaborative environment. We discuss the application of the same generic architecture to the software domain: to develop an environment for independent verification and validation (IV&V) of software. The benefits of the collaborative approach are: early diagnosis of problems, improvement in efficiency and team performance, and consequently cost savings. This will be especially beneficial for IV&V of large software systems. We illustrate the collaborative environment using an example of a software that performs set operations on polygons.<<ETX>>